[Misc] Tiny: Add test network timeouts and dynamic max-parallel for 5090/2-gpu runners#21800
Merged
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
Author
|
/tag-and-rerun-ci |
hnyls2002
requested review from
Fridge003,
Kangyan-Zhou,
bingxche,
ispobock and
merrymercy
as code owners
April 1, 2026 01:17
hnyls2002
changed the title
2 tasks
hnyls2002
added a commit
that referenced
this pull request
Apr 1, 2026
Replace pandas.read_csv(url) with requests.get(url, timeout=120) + pandas.read_csv(io.StringIO(...)) in simple_eval_mmlu.py, simple_eval_gpqa.py, and simple_eval_math.py. Also add timeout=120 to sgl-model-gateway's download_dataset() requests.get call. This extends the timeout coverage from PR #21800 which only fixed simple_eval_common.py and simple_eval_mgsm.py. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
realray808
pushed a commit
to Ascend/sglang
that referenced
this pull request
Apr 3, 2026
* [AMD] Fix AMD CI monitor GitHub API rate limit exhaustion (sgl-project#21527) * [CI] Register missing jit_kernel test files (sgl-project#21547) * [diffusion] fix: return None instead of raising RuntimeError when no model info found (sgl-project#21319) Co-authored-by: Mick <[email protected]> * [rl][sgl] fix tensor mismatch after pause (sgl-project#21514) * [Hicache & JIT_kernel] Support page first layout & mla jit kernel (sgl-project#18311) * test: point DSV3 int8 MLA CI models to lmsys Hugging Face org (sgl-project#21561) * [CI] Relax several thresholds in flaky CIs (sgl-project#21562) * feat: add gc_threshold arg (sgl-project#21481) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Fix flaky test_pp_single_node (sgl-project#21564) * Split workflow for releasing runtime docker (sgl-project#21563) * fix tp capture in vit cuda graph (sgl-project#17255) * [1/n] lora support - Auto detect lora target modules (sgl-project#21439) Co-authored-by: Baizhou Zhang <[email protected]> * [fix] qwen3.5 fuse_moe_triton_tune bug (sgl-project#20232) * Remove sync when enabling return_logprob (sgl-project#20972) * Scope streaming backlog coalescing to incremental_streaming_output mode (sgl-project#21037) Signed-off-by: Vladislav Nosivskoy <[email protected]> Co-authored-by: Lianmin Zheng <[email protected]> * docs: flesh out MAINTAINER.md oncall lists and link GitHub profiles (sgl-project#21575) * [NVIDIA] Enable automatic NUMA configuration (sgl-project#19452) * [diffusion] UX: aggregate expected dtype-cast logs during weight loading (sgl-project#21552) * [diffusion] refactor: Unify `TeaCacheParams` and `WanTeaCacheParams` (sgl-project#20706) Co-authored-by: Mick <[email protected]> * [diffusion] chore: remove redundant identity preprocess_text functions(sgl-project#20633) Co-authored-by: Fengyuan Yu <[email protected]> * Update CODEOWNERS for transformers.py and docs (sgl-project#21555) Co-authored-by: Lianmin Zheng <[email protected]> * reduce CPU peak memory in multimodal tensor hashing (sgl-project#21123) * Fix HFRunner hang when subprocess dies during init (sgl-project#21582) * Fix Piecewise CUDA Graph crash with `-enable-mixed-chunk` (sgl-project#20441) Co-authored-by: jianyingzhu <[email protected]> * [CI] Replace upload/download-artifact with job outputs in release-docker workflow (sgl-project#21579) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Patch transformers is_base_mistral in CI to avoid HF 429 rate limiting (sgl-project#21586) * [CI] Move v32 cp test to deepep running suite (sgl-project#21585) * [AMD] Add GLM-4.7-FP8 accuracy CI test for MI35x (sgl-project#21534) Co-authored-by: Claude Opus 4.6 <[email protected]> * [Clean] Remove deprecated environs (sgl-project#21536) * [diffusion] fix: fix Flux2-Klein prompt tokenization length to 512 and add regression coverage (sgl-project#21407) * [CI] hot-fix ci lint (sgl-project#21608) * [diffusion] feat: support overlay model materialization (sgl-project#21600) * [VLM] Optimize ShmPointerMMData for multi-pickle safety and deferred unwrap (sgl-project#21465) * feat: enable CUDA graph and timestamp for the whisper model(sgl-project#21190) * [NPU] Update quantization&CI documentation (sgl-project#21100) Co-authored-by: Tamir Baydasov <[email protected]> * Skip ci for .md files (sgl-project#21482) * Support skip-softmax attention (sgl-project#19089) * fix: piecewise_cuda_graph get correct qo_indptr (sgl-project#21452) Co-authored-by: Avery Huang <[email protected]> * fix bench_serving sglang backend to support image dataset (sgl-project#21294) * [AMD] Add peft>=0.18.0 to diffusion_hip deps for transformers 5.x compat for AMD diffusion model (sgl-project#21442) Co-authored-by: HaiShaw <[email protected]> * [GDN] Fuse GDN kkt + solve_tril into one kernel (sgl-project#21411) Co-authored-by: luoyuan.luo <[email protected]> * [Diffusion] Align diffusion benchmark skill presets with nightly comparison cases (sgl-project#21616) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Clean up detokenizer and remove dead multimodal_gen code (sgl-project#21588) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Skip flaky elastic EP test (sgl-project#21619) * feat(ci): add GB300 nightly benchmark test suites (sgl-project#21487) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Lossen test_return_routed_experts threshold (sgl-project#21270) * Add subprocess liveness monitor to detect scheduler crashes (sgl-project#18582) Co-authored-by: 继优 <[email protected]> Co-authored-by: shuwenn <[email protected]> * fix: scheduler launch hang when non-current rank dies (sgl-project#20287) * Wrap IPv6 addresses in gRPC, bench_serving, and log messages (sgl-project#21236) Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> * [HiCache] fix: graceful shutdown of pending async tasks in bench_mix.py (sgl-project#20276) * Clean up _wait_for_scheduler_ready implementation (sgl-project#21626) * fix cuda graph capturing error in sm120 mxfp8 triton path (sgl-project#19835) * [sgl] disable piecewise cuda graph when a model doesn't have layers (sgl-project#21565) * [Feature] Optimizations for JPEG input on NVIDIA GPU (sgl-project#19749) * [VLM] perf: optimize CUDA IPC for multimodal transfer by caching IPC pool handles (sgl-project#21418) * [Fix] SGLANG_USE_CUDA_IPC_TRANSPORT=1 and SGLANG_ENABLE_MM_SPLITTING=1 do not work at the same time. (sgl-project#19915) * [Fix] Remove redundant allreduce fusion block and skip TP=1 (sgl-project#20621) * Simplify routed experts test and move base64 encoding to tokenizer manager (sgl-project#21634) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Cleanup] Remove unused BatchMultimodalOutput and BatchMultimodalDecodeReq (sgl-project#21640) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Clean up TokenizerManager: remove dead code and improve rid validation (sgl-project#21639) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * README: coding agent sponsorship for long-term contributors (sgl-project#21642) * Fix circular reference in CustomTestCase.__init_subclass__ (sgl-project#21650) Co-authored-by: wan4ch <[email protected]> * [Fix] Fix Qwen3.5 MoE model loading and Mamba cache sharding in PP mode (sgl-project#21448) Co-authored-by: zhangxiaolei123456 <[email protected]> * [diffusion] CI: fix dashboard chart (nightly) display issues (sgl-project#21653) Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update sponsorship details in README.md (sgl-project#21658) * [Fix] Handle pre-release tags in nightly wheel version parsing (sgl-project#21656) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Intel GPU] Enable DeepSeek R1 inference on XPU (sgl-project#18461) Signed-off-by: P V R K Jyothendra Varma <[email protected]> * [Doc] Update tips for developer new-comers (sgl-project#21659) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [CI] [FlashInfer v0.6.7] Use offline quantized checkpoint for MXFP8 Gemm tests (sgl-project#21625) * MFU metrics in Prometheus (sgl-project#19395) * fix topk softmax performance issue (sgl-project#14702) * [CPU] add kernel apply_rotary_pos_emb_cpu for Qwen3-VL and Qwen3-Omni (sgl-project#13121) Co-authored-by: Ma Mingfei <[email protected]> * [CPU] Implement MXFP4 Gemm kernels for intel AMX to support GPT OSS series. (sgl-project#14385) * [AMD] Fused rope kv store (sgl-project#21315) Co-authored-by: wunhuang <[email protected]> * [NPU] Update DeepSeek-V3.2 model deployment instructions in documentation (sgl-project#21468) Co-authored-by: wuxue (C) <[email protected]> * [AMD] Support AMD MXFP4 Qwen3.5-397B-A17B model (sgl-project#21234) * [Fix] Fix weight_loader property assignment for qwen3-next FP8 models (sgl-project#21662) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * fix mamba cache leak when adder fails to add a matched req. (sgl-project#21404) * fix: Mistral Small 4 fails to start due to config/weight format mismatch (sgl-project#21620) Co-authored-by: mengxiancheng03 <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [diffusion] feat: enhance overlay mechanism (sgl-project#21648) * [diffusion] CI: relax pr-test threshold (sgl-project#21682) * [NPU][Diffusion] fix sp modulate for qwen-image-edit (sgl-project#20974) Co-authored-by: 高鑫 <[email protected]> * [NPU] fix eagle3 accept rate (sgl-project#21255) * DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication (sgl-project#14162) Co-authored-by: undefined <[email protected]> * [NPU] GLM-5 optimize with fused kernels (sgl-project#18617) * [NPU][diffusion]: support parallel decoding of qwen-image (sgl-project#20757) Co-authored-by: 高鑫 <[email protected]> * [diffusion] [NPU] support ring attention on NPU with FA (sgl-project#21383) * [diffusion][doc]: add ring sp performance benchmark page (sgl-project#20998) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [GLM-V and GLM-4.7] Cast to FP32 before gate projection for GLM model. (sgl-project#21660) * fix nemotron capture for non attention layers (sgl-project#21436) * [Bugfix][NPU] Skip FRACTAL_NZ format for MoE weights with unaligned dimensions (sgl-project#21209) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: ronnie_zheng <[email protected]> * [AMD] Add SGLANG_DISAGGREGATION_NUM_PRE_ALLOCATE_REQS env var for configurable KV transfer overlap (sgl-project#20410) Co-authored-by: HaiShaw <[email protected]> * [AMD][MoRI] bump MoRI to v0.1.0 (sgl-project#21673) * [AMD] fix performance regression issue when run gpt-oss with "--context-length 13824" (sgl-project#21691) * Remove flashinfer wheel cache cleanup that deletes other versions (sgl-project#21711) Co-authored-by: Alison Shao <[email protected]> * [misc] multiprocess compilation to speed up test (sgl-project#21483) * Fix human-eval CI install on 5090 runners (sgl-project#21714) Co-authored-by: Alison Shao <[email protected]> * Revert "DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication" (sgl-project#21719) * [Fix] Update supported custom_mem_pool types for mooncake (sgl-project#21728) Co-authored-by: 百麒 <[email protected]> * [Perf]Remove H2D for Qwen3.5 SpecV2 (sgl-project#20864) * [AMD] Fix CI multimodal-gen-test-1-gpu-amd for gen model (sgl-project#21621) * [diffusion] fix: fix Flux.2 with tp(sgl-project#21664) * Add explicit disable flag for FlashInfer allreduce fusion (sgl-project#21446) * [NPU] fix conflict between empty_cache and use_mem_pool (sgl-project#21507) * [AMD] Use tgemm.mm for MoEGate router gemm in deepseek_v2.py (sgl-project#21657) * [CI]Remove msgm-en and mmlu tests which cause timeout (sgl-project#21733) * Fix disaggregation hybrid attention ci (sgl-project#21745) * Rename rerun-ut to rerun-test (sgl-project#21747) * bugfix(model):fix deepstack index out of range error (sgl-project#21727) Co-authored-by: xiaoqi.31 <[email protected]> * [diffusion] fix: fix typo (sgl-project#21746) Signed-off-by: Xiaodong Ye <[email protected]> * [CI] Fix rerun-test suite detection to skip commented registrations (sgl-project#21753) * [PD] Refactor Disagg Conn and Fix Hang with total_request/total_tokens Balancing (sgl-project#21299) Co-authored-by: Weiliangl User <[email protected]> * [CI] Fix ring test timeout (sgl-project#21751) * Enable evict swa with piecewise cuda graph (sgl-project#21754) * Fix kimi-linear launch server error (sgl-project#21752) Co-authored-by: luoyuan.luo <[email protected]> * [PD] Tiny cleanup after KVReceiver refactor (sgl-project#21760) Signed-off-by: Shangming Cai <[email protected]> * Fix remote weight info nnode>1 and dp>1 (sgl-project#17389) * [diffusion] UX: replace deprecated ORJSONResponse with orjson_response (sgl-project#21755) Co-authored-by: Claude Opus 4.6 <[email protected]> * [diffusion] fix: fix Wan2.2-I2V-A14B video max size issue(sgl-project#21390) Signed-off-by: Xiaodong Ye <[email protected]> Co-authored-by: Mick <[email protected]> * [HiMambaTree]: Optimize mamba host lock mechanism (sgl-project#21750) * [AMD] Fix Handle missing rope_theta in get_rope_config for Grok-1 (sgl-project#21518) * [bugfix] Fix rope theta config for MiniMax after transformers v5 update (sgl-project#21241) * Fix ineffective is_base_mistral CI patch for HF API rate limiting (sgl-project#21729) * [2/n] lora - Shared outer experts and support qwen3_30b_a3b_instruct (sgl-project#21466) Co-authored-by: Baizhou Zhang <[email protected]> * Fix cuda graph max bs capture upper bound (sgl-project#21005) * [Fix] Fall back to triton MOE for GPT-OSS on Blackwell with driver >= 595 (sgl-project#21780) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Cache nvidia wheels locally to skip repeated 830 MB downloads in CI (sgl-project#21778) * Add Trivy vulnerability scanning to nightly dev Docker builds (sgl-project#21772) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Remove more redundant PCG tests (sgl-project#21554) * [moe] add customized option to moe-a2a-backend (sgl-project#21786) * Add CompletionSampler for non-chat eval in run_eval (sgl-project#21785) * Remove redundant test_moe_eval_accuracy_large (sgl-project#21787) * Increase hicache eval to 200 examples (sgl-project#21791) * Switch MooncakeSpec to EAGLE3 + Llama-3.1 (sgl-project#21794) * Reduce redundant speculative decoding CI tests (sgl-project#21779) * Fix killall.py crash when sglang is not yet installed (sgl-project#21797) * Remove obsolete sgl-kernel legacy paths (sgl-project#21528) * [jit_kernel] Optimize fused_qknorm_rope: deduplicate sincosf for interleave RoPE (sgl-project#21654) * CUTLASS NVFP4 GEMM improvement of SM120 (sgl-project#21314) * [gRPC] Preserve original ImportError in grpc_server.py (sgl-project#21801) Signed-off-by: Chang Su <[email protected]> * [Misc] Tiny: Add test network timeouts and dynamic max-parallel for 5090/2-gpu runners (sgl-project#21800) * Fix draft extend cuda graph when spec_step=1 (sgl-project#21709) * [Diffusion] Add `--uvicorn-access-log-exclude-prefixes` to suppress noisy access logs (sgl-project#20379) * Add latency and throughput metrics to run_eval (sgl-project#21793) * [diffusion] CI: improve ci reliability (sgl-project#21763) * [bugfix]GLM-4V model (sgl-project#17122) * Fix CVEs in Docker image: pillow, linux-libc-dev, and broken sgl-model-gateway build (sgl-project#21789) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * fix: only showing recent runners from ci failure analysis (sgl-project#21015) * [MPS] Fix Triton stub sub-module imports on Python 3.12+ (sgl-project#21551) Co-authored-by: karanb192 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> * [KDA] Fuse scaled_dot_kkt + solve_tril + recompute_w_u for KDA (sgl-project#21604) Co-authored-by: luoyuan.luo <[email protected]> * chore: bump flashinfer version to 0.6.7 (sgl-project#21422) Co-authored-by: sglang-bot <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> * [3/n] lora moe - Support Qwen3-VL-30B-A3B-Instruct (sgl-project#21469) Co-authored-by: Baizhou Zhang <[email protected]> * [Feature Restoration] repetition_penalty is essential for GLM-V models (sgl-project#21258) Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> * VLM: change default mm-attention backend from triton_attn to fa4 (on blackwell) (sgl-project#21595) * Fix added tokens config with sensible filter (sgl-project#17905) * [AMD] Optimize Qwen3-VL decode - fuse QK-norm + 3D mRoPE + KV cache write (sgl-project#21458) Co-authored-by: Bingxu Chen <[email protected]> Co-authored-by: HaiShaw <[email protected]> * [Bugfix] Fix PP tied embeddings weight loading for qwen3.5 4B dense model (sgl-project#21347) * [CI] Fix lint that was not applied in sgl-project#21458 (sgl-project#21818) * Bug fix for llama eagle3 (sgl-project#21397) * glm_interleave for GLM-V (sgl-project#21671) * style refinement for hisparse (sgl-project#21198) * [Bug][VLM] Fix shared memory race condition in ShmPointerMMData broadcast for multi-GPU VLM serving (sgl-project#21655) * [Bugfix] Fix effective_mamba_size over-allocation (sgl-project#20858) Co-authored-by: Shangming Cai <[email protected]> * Fix in-place mode in pause generation (sgl-project#21705) * [diffusion] fix: respect --prompt-path (sgl-project#21756) * [NPU] update ascend docs (sgl-project#21807) * [VLM] remove AsyncMMDataProcessor wrapper (sgl-project#21651) * Use CustomTestCase for TestSessionControl to enable CI retry (sgl-project#21830) * [NPU]Add a full test pipeline on NPU, resolve issues in the NPU test architecture (sgl-project#20751) * [diffusion][CI]: Add individual component accuracy CI for diffusion models (sgl-project#18709) Co-authored-by: Xiaoyu Zhang <[email protected]> * [Feature] JIT rmsnorm update (with claude) (sgl-project#21834) * [Diffusion][NPU] add ring sp performance benchmark page in npu (sgl-project#21811) * fix(MiMo-V2-Flash): add mimo reasoning parser (sgl-project#21414) * [diffusion] hardware: support FA3 attention backend on MUSA (attn backend, 14/N) (sgl-project#18648) Signed-off-by: Xiaodong Ye <[email protected]> Co-authored-by: Mick <[email protected]> * fix: pre-init tokenizer_manager to avoid AttributeError in shutdown (sgl-project#21824) * [FlashInver v0.6.7] Integrate flashinfer_trtllm mxfp8 gemm (sgl-project#21576) * [Misc] Add network timeout to eval dataset downloads (sgl-project#21873) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [refactor] Clean up duplicate flashinfer trtllm moe code (sgl-project#21233) * [DSA] Support trtllm sparse mla kernel for prefill batches (sgl-project#21783) * [Disagg] GPU staging buffer with dynamic ring allocator for heterogeneous TP KV transfer (sgl-project#19890) * Add merge prohibition policy during CI maintenance mode (sgl-project#21882) * [Misc] Fix comparator e2e tests: add polars dep + fix dp-attention test (sgl-project#21804) Co-authored-by: Alison Shao <[email protected]> * revert: remove TTL-based hard pin from HiRadixCache (sgl-project#21884) * Unify GSM8K eval path to Chat API for regression CI readiness (sgl-project#21667) * [HiCache] fix: Clone host indices to avoid memory leak (sgl-project#21624) Co-authored-by: Zhiqiang Xie <[email protected]> * [HiCache & PD]Fixed detailed cache hit breakdown in PD scenarios. (sgl-project#21764) * [CI] Add Llama 3.1 8B Instruct FP4 CI test on SM120 (sgl-project#20648) * [CI] Add Per-Tensor, Blockwise FP8 Tests on SM120 (sgl-project#20717) Co-authored-by: Brayden Zhong <[email protected]> * Allow /rerun-test to checkout fork PR branch for trusted users (sgl-project#21890) * Direct model loading from object storage with Runai Model Streamer (sgl-project#17948) Signed-off-by: Noa Neria <[email protected]> * fix pcg torch dynamo recompile in mxfp8 Triton path (sgl-project#21888) Co-authored-by: Hanlin Bi <[email protected]> * chore: bump mooncake version to 0.3.10.post1 (sgl-project#21844) * [VLM] Add VLM TP=4 per-commit CI test and improve MMMU eval prompt/parser (sgl-project#21841) * fix(ci): update est_time for 57 tests based on runtime analysis (sgl-project#21896) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Increase multimodal server test timeout from 60 to 90 minutes (sgl-project#21897) * [CI] Remove crashing Kimi K2.5 EAGLE3/MTP variants, keep TP8 and TP8+DP8 (sgl-project#21898) * [diffusion] CI: add initial nvfp4 ci test for b200 (sgl-project#21767) Co-authored-by: Mick <[email protected]> * Migrate all callers from /get_server_info to /server_info (sgl-project#21463) * Support PP key for file backend (sgl-project#21901) * Enable multi-thread weight loading by default (sgl-project#20289) * Skip Go stdlib and NVIDIA tool CVEs in Trivy scan (sgl-project#21905) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Kernel] Fuse temperature + softmax in sampling for decode speedup (sgl-project#20501) * Multi tool streaming fix (sgl-project#20004) * Return HTTP 400 for streaming validation errors (sgl-project#21900) * [Spec][Ngram] 4/N: Remove `max_match_window_size` and `min_match_window_size`, matching all suffixes of the Trie (sgl-project#21225) * Fix ngram doc for speculative_num_draft_tokens default (sgl-project#21910) * [NVIDIA] Enable fp8 flashinfer_trtllm_routed MoE for MiniMax-M2.5 (sgl-project#20394) * scheduler: add prefill-only update in merge batch (sgl-project#21840) * [DSA] Set trtllm kernels as nsa default for Blackwell (sgl-project#21914) * Revert "Rollback flashmla to older version [1/2]" (sgl-project#21922) * test: add manual init test for mooncake transfer engine (sgl-project#21842) Co-authored-by: yunzhi <[email protected]> * Fix spec v2 + logprob when max_num_token is set (sgl-project#20799) * Migrate ngram corpus from torch cpp_extension to TVM FFI jit_kernel (sgl-project#21920) Co-authored-by: DarkSharpness <[email protected]> * [NPU] Support GLM-4.7-Flash on NPU (sgl-project#21408) * [CI] Fix gpu deps import in cpu test (sgl-project#21950) * [Parallel State Refactor 1/n] Remove stream of PyNCCL (sgl-project#20866) * [diffusion] chore: fix stage profiler for multi-stage denoising (sgl-project#21955) * [CI] [Tracing] Add ci for tracing and fix bugs (sgl-project#21740) * Remove logging for subprocess watchdog start (sgl-project#21968) * [4/n] Support gpt oss 20b lora (sgl-project#21570) * [MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine) (sgl-project#17985) Co-authored-by: R0CKSTAR <[email protected]> * [Feature] Stronger transformers modeling backend with TP, PP, MoE, VLMs, and torch compile (sgl-project#19163) * [CI] Remove stale Ascend suite entries from test/srt/run_suite.py (sgl-project#21978) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Skip broken AutoModel mapping entries when resolving Llava submodules (sgl-project#21892) * [CI] Add timeouts to Slack upload urlopen and WebClient (sgl-project#21903) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Diffusion][NPU] Add support for MOVA (sgl-project#21633) Co-authored-by: zhangshuai (S) <[email protected]> * Remove maxItems=1 restriction when tool_choice is specified (sgl-project#20208) * [Feature] NVFP4 Marlin fallback for non-Blackwell GPUs (SM75+) (sgl-project#19652) * [PP] qwen3 vl skip layer id for pp (sgl-project#19135) * [VLM] Enable per-image MM splitting by default and remove MULTI_IMAGES modality (sgl-project#21899) * [Bugfix] Fix incorrect dp-attention parallel info in bench_one_batch (sgl-project#21519) * Revert "[MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine)" (sgl-project#22002) * [NPU] Optimized the wording in the npu docs (sgl-project#21998) * [Parallel State Refactor 2/n] Unify code path of AMD deterministic all reduce (sgl-project#20871) * [AMD] Resolve the performance degression when launch server with "--enable-aiter-allreduce-fusion" (sgl-project#21947) Co-authored-by: wunhuang <[email protected]> * chore: bump sgl-kernel version to 0.4.1 (sgl-project#21447) Co-authored-by: sglang-bot <[email protected]> * [Workflow] Avoid triggering nightly tests in kernel bump workflow (sgl-project#22010) * [Workflow] Fix kernel release jobs skipped on push events (sgl-project#22011) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [PD]: Add support for HiSparse to directly transfer the cache from Prefill to Decode DRAM. (sgl-project#21591) Co-authored-by: Tingwei Huang <[email protected]> Co-authored-by: Shangming Cai <[email protected]> Co-authored-by: Zhiqiang Xie <[email protected]> * [Misc] Update CI permission (sgl-project#22014) * [ROCM][RL] Shuffle Weight In-Place to Preserve Parameter Attributes (sgl-project#21825) * [CI] Fix duplicate job names that bypass branch protection (sgl-project#22001) * fix: remove duplicate words in comments (sgl-project#22007) * [PD] Tiny register info field cleanup for mooncake backend (sgl-project#22016) * [NPU] optimize glm4.7 (sgl-project#19246) * [AMD] Enable FP8 KV cache and FP8 attention kernel for NSA on MI300/MI355 with TileLang backend (sgl-project#21511) * [AMD] Add MiniMax-M2.5 nightly perf benchmarks for MI30x and MI35x (sgl-project#21524) --------- Signed-off-by: Vladislav Nosivskoy <[email protected]> Signed-off-by: P V R K Jyothendra Varma <[email protected]> Signed-off-by: Xiaodong Ye <[email protected]> Signed-off-by: Shangming Cai <[email protected]> Signed-off-by: Chang Su <[email protected]> Signed-off-by: Noa Neria <[email protected]> Co-authored-by: Bingxu Chen <[email protected]> Co-authored-by: Xiaoyu Zhang <[email protected]> Co-authored-by: yang1002378395-cmyk <[email protected]> Co-authored-by: Mick <[email protected]> Co-authored-by: Bi Xue <[email protected]> Co-authored-by: huangtingwei <[email protected]> Co-authored-by: Lianmin Zheng <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> Co-authored-by: Muqi Li <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Qiaolin Yu <[email protected]> Co-authored-by: narutolhy <[email protected]> Co-authored-by: Ethan (Yusheng) Su <[email protected]> Co-authored-by: zhangxiaolei <[email protected]> Co-authored-by: Vladislav Nosivskoy <[email protected]> Co-authored-by: Trevor Morris <[email protected]> Co-authored-by: Eitan Turok <[email protected]> Co-authored-by: Fengyuan Yu <[email protected]> Co-authored-by: Fengyuan Yu <[email protected]> Co-authored-by: Adarsh Shirawalmath <[email protected]> Co-authored-by: Yuhao Yang <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> Co-authored-by: Jianying <[email protected]> Co-authored-by: jianyingzhu <[email protected]> Co-authored-by: Kangyan-Zhou <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: Jacob0226 <[email protected]> Co-authored-by: Aditya Sharma <[email protected]> Co-authored-by: Yuan Luo <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: Артем Савкин <[email protected]> Co-authored-by: Tamir Baydasov <[email protected]> Co-authored-by: Shu Wang <[email protected]> Co-authored-by: eigen <[email protected]> Co-authored-by: Avery Huang <[email protected]> Co-authored-by: jacky.cheng <[email protected]> Co-authored-by: HaiShaw <[email protected]> Co-authored-by: luoyuan.luo <[email protected]> Co-authored-by: Shangming Cai <[email protected]> Co-authored-by: Junrong Lin <[email protected]> Co-authored-by: Simon (Jiyou) Li <[email protected]> Co-authored-by: 继优 <[email protected]> Co-authored-by: shuwenn <[email protected]> Co-authored-by: psaab <[email protected]> Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Hanlin Bi <[email protected]> Co-authored-by: wili <[email protected]> Co-authored-by: saatwiknagpal <[email protected]> Co-authored-by: Mohammad Miadh Angkad <[email protected]> Co-authored-by: wan4ch <[email protected]> Co-authored-by: Feng Su <[email protected]> Co-authored-by: Ying Sheng <[email protected]> Co-authored-by: Polisetty V R K Jyothendra Varma <[email protected]> Co-authored-by: Ziang Li <[email protected]> Co-authored-by: Aishwarya Ramasethu <[email protected]> Co-authored-by: Ma Mingfei <[email protected]> Co-authored-by: blzheng <[email protected]> Co-authored-by: kk <[email protected]> Co-authored-by: wunhuang <[email protected]> Co-authored-by: Michelle Wu <[email protected]> Co-authored-by: wuxue (C) <[email protected]> Co-authored-by: Hubert Lu <[email protected]> Co-authored-by: strgrb <[email protected]> Co-authored-by: LiYomi <[email protected]> Co-authored-by: mengxiancheng03 <[email protected]> Co-authored-by: GXIN <[email protected]> Co-authored-by: 高鑫 <[email protected]> Co-authored-by: heziiop <[email protected]> Co-authored-by: xieminghe1 <[email protected]> Co-authored-by: undefined <[email protected]> Co-authored-by: Makcum888e <[email protected]> Co-authored-by: yuefeng Wu <[email protected]> Co-authored-by: Yuxuan Zhang <[email protected]> Co-authored-by: Vedant V Jhaveri <[email protected]> Co-authored-by: ronnie_zheng <[email protected]> Co-authored-by: Zhai Feiyue <[email protected]> Co-authored-by: jhchouuu <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: DarkSharpness <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: Lewis <[email protected]> Co-authored-by: 百麒 <[email protected]> Co-authored-by: Jincong Chen <[email protected]> Co-authored-by: xiazhahe <[email protected]> Co-authored-by: Thomas Wang <[email protected]> Co-authored-by: Ke Bao <[email protected]> Co-authored-by: xiaoqi <[email protected]> Co-authored-by: xiaoqi.31 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: weireweire <[email protected]> Co-authored-by: Weiliangl User <[email protected]> Co-authored-by: JD <[email protected]> Co-authored-by: Zhangheng <[email protected]> Co-authored-by: Michael <[email protected]> Co-authored-by: Yilong Zhao <[email protected]> Co-authored-by: Johnsonms <[email protected]> Co-authored-by: Brayden Zhong <[email protected]> Co-authored-by: Chang Su <[email protected]> Co-authored-by: KnightLTC <[email protected]> Co-authored-by: Douglas Yang <[email protected]> Co-authored-by: Karan Bansal <[email protected]> Co-authored-by: karanb192 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: sglang-bot <[email protected]> Co-authored-by: sglang-bot <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: sbeurnier <[email protected]> Co-authored-by: YC Yen-Ching Tseng <[email protected]> Co-authored-by: Wenyao Gao <[email protected]> Co-authored-by: Alex Nails <[email protected]> Co-authored-by: khalilzhk <[email protected]> Co-authored-by: Zhiqiang Xie <[email protected]> Co-authored-by: yudian0504 <[email protected]> Co-authored-by: yunkchen <[email protected]> Co-authored-by: wduan-hai <[email protected]> Co-authored-by: amote-i <[email protected]> Co-authored-by: Cherry_ming <[email protected]> Co-authored-by: Ratish P <[email protected]> Co-authored-by: YAMY <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: ishandhanani <[email protected]> Co-authored-by: Derek Yu <[email protected]> Co-authored-by: Noa Neria <[email protected]> Co-authored-by: Hanlin Bi <[email protected]> Co-authored-by: Prozac614 <[email protected]> Co-authored-by: David Cheung <[email protected]> Co-authored-by: Mook <[email protected]> Co-authored-by: Khoa Pham <[email protected]> Co-authored-by: foraxe <[email protected]> Co-authored-by: yunzhi <[email protected]> Co-authored-by: DarkSharpness <[email protected]> Co-authored-by: Todobe <[email protected]> Co-authored-by: ori <[email protected]> Co-authored-by: Thomas <[email protected]> Co-authored-by: zhangshuai (S) <[email protected]> Co-authored-by: lviy <[email protected]> Co-authored-by: Tingwei Huang <[email protected]> Co-authored-by: Yuzhen Zhou <[email protected]> Co-authored-by: Ricardo-M-L <[email protected]> Co-authored-by: Kelon <[email protected]> Co-authored-by: cen121212 <[email protected]>
JustinTong0323
pushed a commit
to JustinTong0323/sglang
that referenced
this pull request
Apr 7, 2026
Hexq0210
pushed a commit
to Ascend/sglang
that referenced
this pull request
Apr 8, 2026
* [NPU] Support GLM-4.7-Flash on NPU (#153) * [NPU] recover accuracy for gemma3-4b-it from 54% to 72% (reduced by transformer5.3) (#155) * [NPU] recover accuracy for gemma3-4b-it for transformer5.3 * Br fix qwen2 5 ascend (#159) * fix qwen2_5_math_rm_72b * add documentation for GLM-4.7-Flash on Ascend (#162) * add documentation for GLM-4.7-Flash * update * Revert "Use LazyValue for routed_experts_weights_of_layer initialization" (#161) Co-authored-by: j30065060 <[email protected]> * fix(grok): fallback to standard weight loading when no presharded files found (#156) Co-authored-by: Jianzhao Xu <[email protected]> * revert: revert qwen3_5.py, use separate layers (#172) * [bugfix]GLM-4V model (#176) Co-authored-by: Jianzhao Xu <[email protected]> * NPU can use piece cuda graph when the piece cuda graph is explicitly declared (#169) Co-authored-by: chx96642264 <[email protected]> * Bug fix for llama eagle3 (#177) * fix eagle3 accept rate (#179) * Support MTP for Qwen3.5 (#154) * feat: support Ascend NPU MTP adaptation for GDN attention backend * fix bug (#181) Co-authored-by: j30065060 <[email protected]> * revert pr 19321 for accuracy temporarily (#178) * revert pr 19321 for accuracy temporarily * Bug fix for not import is npu (#182) * Revert "Revert "Use LazyValue for routed_experts_weights_of_layer initializat…" (#190) * fix: qwen3.5 precision & quant model load error (#191) * [NPU] change fused_qkvzba_split_reshape_cat_npu to fused_qkvzba_split_reshape_cat_contiguous (#198) * [NPU] Use causal_conv1d and fix qwen-next modelslim (#207) * fix: use causal_conv1d from sgl-kernel-npu * merge sgl-project main (#221) * [AMD] Fix AMD CI monitor GitHub API rate limit exhaustion (sgl-project#21527) * [CI] Register missing jit_kernel test files (sgl-project#21547) * [diffusion] fix: return None instead of raising RuntimeError when no model info found (sgl-project#21319) Co-authored-by: Mick <[email protected]> * [rl][sgl] fix tensor mismatch after pause (sgl-project#21514) * [Hicache & JIT_kernel] Support page first layout & mla jit kernel (sgl-project#18311) * test: point DSV3 int8 MLA CI models to lmsys Hugging Face org (sgl-project#21561) * [CI] Relax several thresholds in flaky CIs (sgl-project#21562) * feat: add gc_threshold arg (sgl-project#21481) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Fix flaky test_pp_single_node (sgl-project#21564) * Split workflow for releasing runtime docker (sgl-project#21563) * fix tp capture in vit cuda graph (sgl-project#17255) * [1/n] lora support - Auto detect lora target modules (sgl-project#21439) Co-authored-by: Baizhou Zhang <[email protected]> * [fix] qwen3.5 fuse_moe_triton_tune bug (sgl-project#20232) * Remove sync when enabling return_logprob (sgl-project#20972) * Scope streaming backlog coalescing to incremental_streaming_output mode (sgl-project#21037) Signed-off-by: Vladislav Nosivskoy <[email protected]> Co-authored-by: Lianmin Zheng <[email protected]> * docs: flesh out MAINTAINER.md oncall lists and link GitHub profiles (sgl-project#21575) * [NVIDIA] Enable automatic NUMA configuration (sgl-project#19452) * [diffusion] UX: aggregate expected dtype-cast logs during weight loading (sgl-project#21552) * [diffusion] refactor: Unify `TeaCacheParams` and `WanTeaCacheParams` (sgl-project#20706) Co-authored-by: Mick <[email protected]> * [diffusion] chore: remove redundant identity preprocess_text functions(sgl-project#20633) Co-authored-by: Fengyuan Yu <[email protected]> * Update CODEOWNERS for transformers.py and docs (sgl-project#21555) Co-authored-by: Lianmin Zheng <[email protected]> * reduce CPU peak memory in multimodal tensor hashing (sgl-project#21123) * Fix HFRunner hang when subprocess dies during init (sgl-project#21582) * Fix Piecewise CUDA Graph crash with `-enable-mixed-chunk` (sgl-project#20441) Co-authored-by: jianyingzhu <[email protected]> * [CI] Replace upload/download-artifact with job outputs in release-docker workflow (sgl-project#21579) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Patch transformers is_base_mistral in CI to avoid HF 429 rate limiting (sgl-project#21586) * [CI] Move v32 cp test to deepep running suite (sgl-project#21585) * [AMD] Add GLM-4.7-FP8 accuracy CI test for MI35x (sgl-project#21534) Co-authored-by: Claude Opus 4.6 <[email protected]> * [Clean] Remove deprecated environs (sgl-project#21536) * [diffusion] fix: fix Flux2-Klein prompt tokenization length to 512 and add regression coverage (sgl-project#21407) * [CI] hot-fix ci lint (sgl-project#21608) * [diffusion] feat: support overlay model materialization (sgl-project#21600) * [VLM] Optimize ShmPointerMMData for multi-pickle safety and deferred unwrap (sgl-project#21465) * feat: enable CUDA graph and timestamp for the whisper model(sgl-project#21190) * [NPU] Update quantization&CI documentation (sgl-project#21100) Co-authored-by: Tamir Baydasov <[email protected]> * Skip ci for .md files (sgl-project#21482) * Support skip-softmax attention (sgl-project#19089) * fix: piecewise_cuda_graph get correct qo_indptr (sgl-project#21452) Co-authored-by: Avery Huang <[email protected]> * fix bench_serving sglang backend to support image dataset (sgl-project#21294) * [AMD] Add peft>=0.18.0 to diffusion_hip deps for transformers 5.x compat for AMD diffusion model (sgl-project#21442) Co-authored-by: HaiShaw <[email protected]> * [GDN] Fuse GDN kkt + solve_tril into one kernel (sgl-project#21411) Co-authored-by: luoyuan.luo <[email protected]> * [Diffusion] Align diffusion benchmark skill presets with nightly comparison cases (sgl-project#21616) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Clean up detokenizer and remove dead multimodal_gen code (sgl-project#21588) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Skip flaky elastic EP test (sgl-project#21619) * feat(ci): add GB300 nightly benchmark test suites (sgl-project#21487) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Lossen test_return_routed_experts threshold (sgl-project#21270) * Add subprocess liveness monitor to detect scheduler crashes (sgl-project#18582) Co-authored-by: 继优 <[email protected]> Co-authored-by: shuwenn <[email protected]> * fix: scheduler launch hang when non-current rank dies (sgl-project#20287) * Wrap IPv6 addresses in gRPC, bench_serving, and log messages (sgl-project#21236) Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> * [HiCache] fix: graceful shutdown of pending async tasks in bench_mix.py (sgl-project#20276) * Clean up _wait_for_scheduler_ready implementation (sgl-project#21626) * fix cuda graph capturing error in sm120 mxfp8 triton path (sgl-project#19835) * [sgl] disable piecewise cuda graph when a model doesn't have layers (sgl-project#21565) * [Feature] Optimizations for JPEG input on NVIDIA GPU (sgl-project#19749) * [VLM] perf: optimize CUDA IPC for multimodal transfer by caching IPC pool handles (sgl-project#21418) * [Fix] SGLANG_USE_CUDA_IPC_TRANSPORT=1 and SGLANG_ENABLE_MM_SPLITTING=1 do not work at the same time. (sgl-project#19915) * [Fix] Remove redundant allreduce fusion block and skip TP=1 (sgl-project#20621) * Simplify routed experts test and move base64 encoding to tokenizer manager (sgl-project#21634) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Cleanup] Remove unused BatchMultimodalOutput and BatchMultimodalDecodeReq (sgl-project#21640) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Clean up TokenizerManager: remove dead code and improve rid validation (sgl-project#21639) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * README: coding agent sponsorship for long-term contributors (sgl-project#21642) * Fix circular reference in CustomTestCase.__init_subclass__ (sgl-project#21650) Co-authored-by: wan4ch <[email protected]> * [Fix] Fix Qwen3.5 MoE model loading and Mamba cache sharding in PP mode (sgl-project#21448) Co-authored-by: zhangxiaolei123456 <[email protected]> * [diffusion] CI: fix dashboard chart (nightly) display issues (sgl-project#21653) Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update sponsorship details in README.md (sgl-project#21658) * [Fix] Handle pre-release tags in nightly wheel version parsing (sgl-project#21656) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Intel GPU] Enable DeepSeek R1 inference on XPU (sgl-project#18461) Signed-off-by: P V R K Jyothendra Varma <[email protected]> * [Doc] Update tips for developer new-comers (sgl-project#21659) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [CI] [FlashInfer v0.6.7] Use offline quantized checkpoint for MXFP8 Gemm tests (sgl-project#21625) * MFU metrics in Prometheus (sgl-project#19395) * fix topk softmax performance issue (sgl-project#14702) * [CPU] add kernel apply_rotary_pos_emb_cpu for Qwen3-VL and Qwen3-Omni (sgl-project#13121) Co-authored-by: Ma Mingfei <[email protected]> * [CPU] Implement MXFP4 Gemm kernels for intel AMX to support GPT OSS series. (sgl-project#14385) * [AMD] Fused rope kv store (sgl-project#21315) Co-authored-by: wunhuang <[email protected]> * [NPU] Update DeepSeek-V3.2 model deployment instructions in documentation (sgl-project#21468) Co-authored-by: wuxue (C) <[email protected]> * [AMD] Support AMD MXFP4 Qwen3.5-397B-A17B model (sgl-project#21234) * [Fix] Fix weight_loader property assignment for qwen3-next FP8 models (sgl-project#21662) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * fix mamba cache leak when adder fails to add a matched req. (sgl-project#21404) * fix: Mistral Small 4 fails to start due to config/weight format mismatch (sgl-project#21620) Co-authored-by: mengxiancheng03 <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [diffusion] feat: enhance overlay mechanism (sgl-project#21648) * [diffusion] CI: relax pr-test threshold (sgl-project#21682) * [NPU][Diffusion] fix sp modulate for qwen-image-edit (sgl-project#20974) Co-authored-by: 高鑫 <[email protected]> * [NPU] fix eagle3 accept rate (sgl-project#21255) * DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication (sgl-project#14162) Co-authored-by: undefined <[email protected]> * [NPU] GLM-5 optimize with fused kernels (sgl-project#18617) * [NPU][diffusion]: support parallel decoding of qwen-image (sgl-project#20757) Co-authored-by: 高鑫 <[email protected]> * [diffusion] [NPU] support ring attention on NPU with FA (sgl-project#21383) * [diffusion][doc]: add ring sp performance benchmark page (sgl-project#20998) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * [GLM-V and GLM-4.7] Cast to FP32 before gate projection for GLM model. (sgl-project#21660) * fix nemotron capture for non attention layers (sgl-project#21436) * [Bugfix][NPU] Skip FRACTAL_NZ format for MoE weights with unaligned dimensions (sgl-project#21209) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: ronnie_zheng <[email protected]> * [AMD] Add SGLANG_DISAGGREGATION_NUM_PRE_ALLOCATE_REQS env var for configurable KV transfer overlap (sgl-project#20410) Co-authored-by: HaiShaw <[email protected]> * [AMD][MoRI] bump MoRI to v0.1.0 (sgl-project#21673) * [AMD] fix performance regression issue when run gpt-oss with "--context-length 13824" (sgl-project#21691) * Remove flashinfer wheel cache cleanup that deletes other versions (sgl-project#21711) Co-authored-by: Alison Shao <[email protected]> * [misc] multiprocess compilation to speed up test (sgl-project#21483) * Fix human-eval CI install on 5090 runners (sgl-project#21714) Co-authored-by: Alison Shao <[email protected]> * Revert "DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication" (sgl-project#21719) * [Fix] Update supported custom_mem_pool types for mooncake (sgl-project#21728) Co-authored-by: 百麒 <[email protected]> * [Perf]Remove H2D for Qwen3.5 SpecV2 (sgl-project#20864) * [AMD] Fix CI multimodal-gen-test-1-gpu-amd for gen model (sgl-project#21621) * [diffusion] fix: fix Flux.2 with tp(sgl-project#21664) * Add explicit disable flag for FlashInfer allreduce fusion (sgl-project#21446) * [NPU] fix conflict between empty_cache and use_mem_pool (sgl-project#21507) * [AMD] Use tgemm.mm for MoEGate router gemm in deepseek_v2.py (sgl-project#21657) * [CI]Remove msgm-en and mmlu tests which cause timeout (sgl-project#21733) * Fix disaggregation hybrid attention ci (sgl-project#21745) * Rename rerun-ut to rerun-test (sgl-project#21747) * bugfix(model):fix deepstack index out of range error (sgl-project#21727) Co-authored-by: xiaoqi.31 <[email protected]> * [diffusion] fix: fix typo (sgl-project#21746) Signed-off-by: Xiaodong Ye <[email protected]> * [CI] Fix rerun-test suite detection to skip commented registrations (sgl-project#21753) * [PD] Refactor Disagg Conn and Fix Hang with total_request/total_tokens Balancing (sgl-project#21299) Co-authored-by: Weiliangl User <[email protected]> * [CI] Fix ring test timeout (sgl-project#21751) * Enable evict swa with piecewise cuda graph (sgl-project#21754) * Fix kimi-linear launch server error (sgl-project#21752) Co-authored-by: luoyuan.luo <[email protected]> * [PD] Tiny cleanup after KVReceiver refactor (sgl-project#21760) Signed-off-by: Shangming Cai <[email protected]> * Fix remote weight info nnode>1 and dp>1 (sgl-project#17389) * [diffusion] UX: replace deprecated ORJSONResponse with orjson_response (sgl-project#21755) Co-authored-by: Claude Opus 4.6 <[email protected]> * [diffusion] fix: fix Wan2.2-I2V-A14B video max size issue(sgl-project#21390) Signed-off-by: Xiaodong Ye <[email protected]> Co-authored-by: Mick <[email protected]> * [HiMambaTree]: Optimize mamba host lock mechanism (sgl-project#21750) * [AMD] Fix Handle missing rope_theta in get_rope_config for Grok-1 (sgl-project#21518) * [bugfix] Fix rope theta config for MiniMax after transformers v5 update (sgl-project#21241) * Fix ineffective is_base_mistral CI patch for HF API rate limiting (sgl-project#21729) * [2/n] lora - Shared outer experts and support qwen3_30b_a3b_instruct (sgl-project#21466) Co-authored-by: Baizhou Zhang <[email protected]> * Fix cuda graph max bs capture upper bound (sgl-project#21005) * [Fix] Fall back to triton MOE for GPT-OSS on Blackwell with driver >= 595 (sgl-project#21780) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Cache nvidia wheels locally to skip repeated 830 MB downloads in CI (sgl-project#21778) * Add Trivy vulnerability scanning to nightly dev Docker builds (sgl-project#21772) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Remove more redundant PCG tests (sgl-project#21554) * [moe] add customized option to moe-a2a-backend (sgl-project#21786) * Add CompletionSampler for non-chat eval in run_eval (sgl-project#21785) * Remove redundant test_moe_eval_accuracy_large (sgl-project#21787) * Increase hicache eval to 200 examples (sgl-project#21791) * Switch MooncakeSpec to EAGLE3 + Llama-3.1 (sgl-project#21794) * Reduce redundant speculative decoding CI tests (sgl-project#21779) * Fix killall.py crash when sglang is not yet installed (sgl-project#21797) * Remove obsolete sgl-kernel legacy paths (sgl-project#21528) * [jit_kernel] Optimize fused_qknorm_rope: deduplicate sincosf for interleave RoPE (sgl-project#21654) * CUTLASS NVFP4 GEMM improvement of SM120 (sgl-project#21314) * [gRPC] Preserve original ImportError in grpc_server.py (sgl-project#21801) Signed-off-by: Chang Su <[email protected]> * [Misc] Tiny: Add test network timeouts and dynamic max-parallel for 5090/2-gpu runners (sgl-project#21800) * Fix draft extend cuda graph when spec_step=1 (sgl-project#21709) * [Diffusion] Add `--uvicorn-access-log-exclude-prefixes` to suppress noisy access logs (sgl-project#20379) * Add latency and throughput metrics to run_eval (sgl-project#21793) * [diffusion] CI: improve ci reliability (sgl-project#21763) * [bugfix]GLM-4V model (sgl-project#17122) * Fix CVEs in Docker image: pillow, linux-libc-dev, and broken sgl-model-gateway build (sgl-project#21789) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * fix: only showing recent runners from ci failure analysis (sgl-project#21015) * [MPS] Fix Triton stub sub-module imports on Python 3.12+ (sgl-project#21551) Co-authored-by: karanb192 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> * [KDA] Fuse scaled_dot_kkt + solve_tril + recompute_w_u for KDA (sgl-project#21604) Co-authored-by: luoyuan.luo <[email protected]> * chore: bump flashinfer version to 0.6.7 (sgl-project#21422) Co-authored-by: sglang-bot <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> * [3/n] lora moe - Support Qwen3-VL-30B-A3B-Instruct (sgl-project#21469) Co-authored-by: Baizhou Zhang <[email protected]> * [Feature Restoration] repetition_penalty is essential for GLM-V models (sgl-project#21258) Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> * VLM: change default mm-attention backend from triton_attn to fa4 (on blackwell) (sgl-project#21595) * Fix added tokens config with sensible filter (sgl-project#17905) * [AMD] Optimize Qwen3-VL decode - fuse QK-norm + 3D mRoPE + KV cache write (sgl-project#21458) Co-authored-by: Bingxu Chen <[email protected]> Co-authored-by: HaiShaw <[email protected]> * [Bugfix] Fix PP tied embeddings weight loading for qwen3.5 4B dense model (sgl-project#21347) * [CI] Fix lint that was not applied in sgl-project#21458 (sgl-project#21818) * Bug fix for llama eagle3 (sgl-project#21397) * glm_interleave for GLM-V (sgl-project#21671) * style refinement for hisparse (sgl-project#21198) * [Bug][VLM] Fix shared memory race condition in ShmPointerMMData broadcast for multi-GPU VLM serving (sgl-project#21655) * [Bugfix] Fix effective_mamba_size over-allocation (sgl-project#20858) Co-authored-by: Shangming Cai <[email protected]> * Fix in-place mode in pause generation (sgl-project#21705) * [diffusion] fix: respect --prompt-path (sgl-project#21756) * [NPU] update ascend docs (sgl-project#21807) * [VLM] remove AsyncMMDataProcessor wrapper (sgl-project#21651) * Use CustomTestCase for TestSessionControl to enable CI retry (sgl-project#21830) * [NPU]Add a full test pipeline on NPU, resolve issues in the NPU test architecture (sgl-project#20751) * [diffusion][CI]: Add individual component accuracy CI for diffusion models (sgl-project#18709) Co-authored-by: Xiaoyu Zhang <[email protected]> * [Feature] JIT rmsnorm update (with claude) (sgl-project#21834) * [Diffusion][NPU] add ring sp performance benchmark page in npu (sgl-project#21811) * fix(MiMo-V2-Flash): add mimo reasoning parser (sgl-project#21414) * [diffusion] hardware: support FA3 attention backend on MUSA (attn backend, 14/N) (sgl-project#18648) Signed-off-by: Xiaodong Ye <[email protected]> Co-authored-by: Mick <[email protected]> * fix: pre-init tokenizer_manager to avoid AttributeError in shutdown (sgl-project#21824) * [FlashInver v0.6.7] Integrate flashinfer_trtllm mxfp8 gemm (sgl-project#21576) * [Misc] Add network timeout to eval dataset downloads (sgl-project#21873) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [refactor] Clean up duplicate flashinfer trtllm moe code (sgl-project#21233) * [DSA] Support trtllm sparse mla kernel for prefill batches (sgl-project#21783) * [Disagg] GPU staging buffer with dynamic ring allocator for heterogeneous TP KV transfer (sgl-project#19890) * Add merge prohibition policy during CI maintenance mode (sgl-project#21882) * [Misc] Fix comparator e2e tests: add polars dep + fix dp-attention test (sgl-project#21804) Co-authored-by: Alison Shao <[email protected]> * revert: remove TTL-based hard pin from HiRadixCache (sgl-project#21884) * Unify GSM8K eval path to Chat API for regression CI readiness (sgl-project#21667) * [HiCache] fix: Clone host indices to avoid memory leak (sgl-project#21624) Co-authored-by: Zhiqiang Xie <[email protected]> * [HiCache & PD]Fixed detailed cache hit breakdown in PD scenarios. (sgl-project#21764) * [CI] Add Llama 3.1 8B Instruct FP4 CI test on SM120 (sgl-project#20648) * [CI] Add Per-Tensor, Blockwise FP8 Tests on SM120 (sgl-project#20717) Co-authored-by: Brayden Zhong <[email protected]> * Allow /rerun-test to checkout fork PR branch for trusted users (sgl-project#21890) * Direct model loading from object storage with Runai Model Streamer (sgl-project#17948) Signed-off-by: Noa Neria <[email protected]> * fix pcg torch dynamo recompile in mxfp8 Triton path (sgl-project#21888) Co-authored-by: Hanlin Bi <[email protected]> * chore: bump mooncake version to 0.3.10.post1 (sgl-project#21844) * [VLM] Add VLM TP=4 per-commit CI test and improve MMMU eval prompt/parser (sgl-project#21841) * fix(ci): update est_time for 57 tests based on runtime analysis (sgl-project#21896) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [CI] Increase multimodal server test timeout from 60 to 90 minutes (sgl-project#21897) * [CI] Remove crashing Kimi K2.5 EAGLE3/MTP variants, keep TP8 and TP8+DP8 (sgl-project#21898) * [diffusion] CI: add initial nvfp4 ci test for b200 (sgl-project#21767) Co-authored-by: Mick <[email protected]> * Migrate all callers from /get_server_info to /server_info (sgl-project#21463) * Support PP key for file backend (sgl-project#21901) * Enable multi-thread weight loading by default (sgl-project#20289) * Skip Go stdlib and NVIDIA tool CVEs in Trivy scan (sgl-project#21905) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Kernel] Fuse temperature + softmax in sampling for decode speedup (sgl-project#20501) * Multi tool streaming fix (sgl-project#20004) * Return HTTP 400 for streaming validation errors (sgl-project#21900) * [Spec][Ngram] 4/N: Remove `max_match_window_size` and `min_match_window_size`, matching all suffixes of the Trie (sgl-project#21225) * Fix ngram doc for speculative_num_draft_tokens default (sgl-project#21910) * [NVIDIA] Enable fp8 flashinfer_trtllm_routed MoE for MiniMax-M2.5 (sgl-project#20394) * scheduler: add prefill-only update in merge batch (sgl-project#21840) * [DSA] Set trtllm kernels as nsa default for Blackwell (sgl-project#21914) * Revert "Rollback flashmla to older version [1/2]" (sgl-project#21922) * test: add manual init test for mooncake transfer engine (sgl-project#21842) Co-authored-by: yunzhi <[email protected]> * Fix spec v2 + logprob when max_num_token is set (sgl-project#20799) * Migrate ngram corpus from torch cpp_extension to TVM FFI jit_kernel (sgl-project#21920) Co-authored-by: DarkSharpness <[email protected]> * [NPU] Support GLM-4.7-Flash on NPU (sgl-project#21408) * [CI] Fix gpu deps import in cpu test (sgl-project#21950) * [Parallel State Refactor 1/n] Remove stream of PyNCCL (sgl-project#20866) * [diffusion] chore: fix stage profiler for multi-stage denoising (sgl-project#21955) * [CI] [Tracing] Add ci for tracing and fix bugs (sgl-project#21740) * Remove logging for subprocess watchdog start (sgl-project#21968) * [4/n] Support gpt oss 20b lora (sgl-project#21570) * [MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine) (sgl-project#17985) Co-authored-by: R0CKSTAR <[email protected]> * [Feature] Stronger transformers modeling backend with TP, PP, MoE, VLMs, and torch compile (sgl-project#19163) * [CI] Remove stale Ascend suite entries from test/srt/run_suite.py (sgl-project#21978) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Skip broken AutoModel mapping entries when resolving Llava submodules (sgl-project#21892) * [CI] Add timeouts to Slack upload urlopen and WebClient (sgl-project#21903) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [Diffusion][NPU] Add support for MOVA (sgl-project#21633) Co-authored-by: zhangshuai (S) <[email protected]> * Remove maxItems=1 restriction when tool_choice is specified (sgl-project#20208) * [Feature] NVFP4 Marlin fallback for non-Blackwell GPUs (SM75+) (sgl-project#19652) * [PP] qwen3 vl skip layer id for pp (sgl-project#19135) * [VLM] Enable per-image MM splitting by default and remove MULTI_IMAGES modality (sgl-project#21899) * [Bugfix] Fix incorrect dp-attention parallel info in bench_one_batch (sgl-project#21519) * Revert "[MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine)" (sgl-project#22002) * [NPU] Optimized the wording in the npu docs (sgl-project#21998) * [Parallel State Refactor 2/n] Unify code path of AMD deterministic all reduce (sgl-project#20871) * [AMD] Resolve the performance degression when launch server with "--enable-aiter-allreduce-fusion" (sgl-project#21947) Co-authored-by: wunhuang <[email protected]> * chore: bump sgl-kernel version to 0.4.1 (sgl-project#21447) Co-authored-by: sglang-bot <[email protected]> * [Workflow] Avoid triggering nightly tests in kernel bump workflow (sgl-project#22010) * [Workflow] Fix kernel release jobs skipped on push events (sgl-project#22011) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * [PD]: Add support for HiSparse to directly transfer the cache from Prefill to Decode DRAM. (sgl-project#21591) Co-authored-by: Tingwei Huang <[email protected]> Co-authored-by: Shangming Cai <[email protected]> Co-authored-by: Zhiqiang Xie <[email protected]> * [Misc] Update CI permission (sgl-project#22014) * [ROCM][RL] Shuffle Weight In-Place to Preserve Parameter Attributes (sgl-project#21825) * [CI] Fix duplicate job names that bypass branch protection (sgl-project#22001) * fix: remove duplicate words in comments (sgl-project#22007) * [PD] Tiny register info field cleanup for mooncake backend (sgl-project#22016) * [NPU] optimize glm4.7 (sgl-project#19246) * [AMD] Enable FP8 KV cache and FP8 attention kernel for NSA on MI300/MI355 with TileLang backend (sgl-project#21511) * [AMD] Add MiniMax-M2.5 nightly perf benchmarks for MI30x and MI35x (sgl-project#21524) --------- Signed-off-by: Vladislav Nosivskoy <[email protected]> Signed-off-by: P V R K Jyothendra Varma <[email protected]> Signed-off-by: Xiaodong Ye <[email protected]> Signed-off-by: Shangming Cai <[email protected]> Signed-off-by: Chang Su <[email protected]> Signed-off-by: Noa Neria <[email protected]> Co-authored-by: Bingxu Chen <[email protected]> Co-authored-by: Xiaoyu Zhang <[email protected]> Co-authored-by: yang1002378395-cmyk <[email protected]> Co-authored-by: Mick <[email protected]> Co-authored-by: Bi Xue <[email protected]> Co-authored-by: huangtingwei <[email protected]> Co-authored-by: Lianmin Zheng <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> Co-authored-by: Muqi Li <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Qiaolin Yu <[email protected]> Co-authored-by: narutolhy <[email protected]> Co-authored-by: Ethan (Yusheng) Su <[email protected]> Co-authored-by: zhangxiaolei <[email protected]> Co-authored-by: Vladislav Nosivskoy <[email protected]> Co-authored-by: Trevor Morris <[email protected]> Co-authored-by: Eitan Turok <[email protected]> Co-authored-by: Fengyuan Yu <[email protected]> Co-authored-by: Fengyuan Yu <[email protected]> Co-authored-by: Adarsh Shirawalmath <[email protected]> Co-authored-by: Yuhao Yang <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> Co-authored-by: Jianying <[email protected]> Co-authored-by: jianyingzhu <[email protected]> Co-authored-by: Kangyan-Zhou <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: Jacob0226 <[email protected]> Co-authored-by: Aditya Sharma <[email protected]> Co-authored-by: Yuan Luo <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: Артем Савкин <[email protected]> Co-authored-by: Tamir Baydasov <[email protected]> Co-authored-by: Shu Wang <[email protected]> Co-authored-by: eigen <[email protected]> Co-authored-by: Avery Huang <[email protected]> Co-authored-by: jacky.cheng <[email protected]> Co-authored-by: HaiShaw <[email protected]> Co-authored-by: luoyuan.luo <[email protected]> Co-authored-by: Shangming Cai <[email protected]> Co-authored-by: Junrong Lin <[email protected]> Co-authored-by: Simon (Jiyou) Li <[email protected]> Co-authored-by: 继优 <[email protected]> Co-authored-by: shuwenn <[email protected]> Co-authored-by: psaab <[email protected]> Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Hanlin Bi <[email protected]> Co-authored-by: wili <[email protected]> Co-authored-by: saatwiknagpal <[email protected]> Co-authored-by: Mohammad Miadh Angkad <[email protected]> Co-authored-by: wan4ch <[email protected]> Co-authored-by: Feng Su <[email protected]> Co-authored-by: Ying Sheng <[email protected]> Co-authored-by: Polisetty V R K Jyothendra Varma <[email protected]> Co-authored-by: Ziang Li <[email protected]> Co-authored-by: Aishwarya Ramasethu <[email protected]> Co-authored-by: Ma Mingfei <[email protected]> Co-authored-by: blzheng <[email protected]> Co-authored-by: kk <[email protected]> Co-authored-by: wunhuang <[email protected]> Co-authored-by: Michelle Wu <[email protected]> Co-authored-by: wuxue (C) <[email protected]> Co-authored-by: Hubert Lu <[email protected]> Co-authored-by: strgrb <[email protected]> Co-authored-by: LiYomi <[email protected]> Co-authored-by: mengxiancheng03 <[email protected]> Co-authored-by: GXIN <[email protected]> Co-authored-by: 高鑫 <[email protected]> Co-authored-by: heziiop <[email protected]> Co-authored-by: xieminghe1 <[email protected]> Co-authored-by: undefined <[email protected]> Co-authored-by: Makcum888e <[email protected]> Co-authored-by: yuefeng Wu <[email protected]> Co-authored-by: Yuxuan Zhang <[email protected]> Co-authored-by: Vedant V Jhaveri <[email protected]> Co-authored-by: ronnie_zheng <[email protected]> Co-authored-by: Zhai Feiyue <[email protected]> Co-authored-by: jhchouuu <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: DarkSharpness <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: Lewis <[email protected]> Co-authored-by: 百麒 <[email protected]> Co-authored-by: Jincong Chen <[email protected]> Co-authored-by: xiazhahe <[email protected]> Co-authored-by: Thomas Wang <[email protected]> Co-authored-by: Ke Bao <[email protected]> Co-authored-by: xiaoqi <[email protected]> Co-authored-by: xiaoqi.31 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: weireweire <[email protected]> Co-authored-by: Weiliangl User <[email protected]> Co-authored-by: JD <[email protected]> Co-authored-by: Zhangheng <[email protected]> Co-authored-by: Michael <[email protected]> Co-authored-by: Yilong Zhao <[email protected]> Co-authored-by: Johnsonms <[email protected]> Co-authored-by: Brayden Zhong <[email protected]> Co-authored-by: Chang Su <[email protected]> Co-authored-by: KnightLTC <[email protected]> Co-authored-by: Douglas Yang <[email protected]> Co-authored-by: Karan Bansal <[email protected]> Co-authored-by: karanb192 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: sglang-bot <[email protected]> Co-authored-by: sglang-bot <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: sbeurnier <[email protected]> Co-authored-by: YC Yen-Ching Tseng <[email protected]> Co-authored-by: Wenyao Gao <[email protected]> Co-authored-by: Alex Nails <[email protected]> Co-authored-by: khalilzhk <[email protected]> Co-authored-by: Zhiqiang Xie <[email protected]> Co-authored-by: yudian0504 <[email protected]> Co-authored-by: yunkchen <[email protected]> Co-authored-by: wduan-hai <[email protected]> Co-authored-by: amote-i <[email protected]> Co-authored-by: Cherry_ming <[email protected]> Co-authored-by: Ratish P <[email protected]> Co-authored-by: YAMY <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: ishandhanani <[email protected]> Co-authored-by: Derek Yu <[email protected]> Co-authored-by: Noa Neria <[email protected]> Co-authored-by: Hanlin Bi <[email protected]> Co-authored-by: Prozac614 <[email protected]> Co-authored-by: David Cheung <[email protected]> Co-authored-by: Mook <[email protected]> Co-authored-by: Khoa Pham <[email protected]> Co-authored-by: foraxe <[email protected]> Co-authored-by: yunzhi <[email protected]> Co-authored-by: DarkSharpness <[email protected]> Co-authored-by: Todobe <[email protected]> Co-authored-by: ori <[email protected]> Co-authored-by: Thomas <[email protected]> Co-authored-by: zhangshuai (S) <[email protected]> Co-authored-by: lviy <[email protected]> Co-authored-by: Tingwei Huang <[email protected]> Co-authored-by: Yuzhen Zhou <[email protected]> Co-authored-by: Ricardo-M-L <[email protected]> Co-authored-by: Kelon <[email protected]> Co-authored-by: cen121212 <[email protected]> * BugFix for MLAPO for Deepseek eagle3 on Ascend (#222) * adapt mtp + prefix for ascend gdn backend (#202) * Minimax 2.5 optimization (#237) * Move ring test to nightly (sgl-project#22267) * [diffusion] CI: fix consistency check (sgl-project#22251) * [Disagg][NIXL] Support Mamba state slice transfer for heterogeneous TP (Step 2/2 for Qwen3.5) (sgl-project#22240) * [Mamba] eliminate D2H if tracking mamba states (sgl-project#20522) Co-authored-by: hzh0425 <[email protected]> * fix: Auto-correct page_size for Mamba no_buffer radix cache mode (sgl-project#20538) * Support HTTP2 server (sgl-project#21700) * [NPU] enable mla prepare fused kernel only when being mla attn (sgl-project#22024) * [HiSparse] Optimize the scheduling of decode backup. (sgl-project#21932) Co-authored-by: hzh0425 <[email protected]> Co-authored-by: Zhiqiang Xie <[email protected]> * Kernels community fa3 (sgl-project#20796) * [tiny] migrate /get_server_info; print accept length in accuracy tests (sgl-project#22282) * [AMD] Fix test_kimi_k25_mxfp4.py : stage-c-test-large-8-gpu-amd-mi35x (linux-mi35x-gpu-8, 1) (sgl-project#22188) * [Feature] Add DFLASH speculative decoding support (sgl-project#22077) Co-authored-by: Jian Chen <[email protected]> Co-authored-by: Zhijian Liu <[email protected]> Co-authored-by: Richard Gong <[email protected]> Co-authored-by: David Wang <[email protected]> Co-authored-by: yilian49 <[email protected]> Co-authored-by: xm:D <[email protected]> * Reduce unnecessary kernels and copies in the NSA indexer (sgl-project#22232) * [CI] Update nightly test models for H200/B200 (sgl-project#22288) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> * Add fast-fail to multimodal-gen CI (sgl-project#22284) * [NVIDIA] Enable FP4 flashinfer trtllm routed moe (sgl-project#21240) * [CI] Migrate mgsm_en eval to gsm8k to remove openaipublic dependency (sgl-project#21931) Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Kangyan-Zhou <[email protected]> * Revert "[CI] Update nightly test models for H200/B200 (sgl-project#22288)" (sgl-project#22297) * Only upload CUDA coredumps on test failure (sgl-project#22301) --------- Signed-off-by: Vladislav Nosivskoy <[email protected]> Signed-off-by: P V R K Jyothendra Varma <[email protected]> Signed-off-by: Xiaodong Ye <[email protected]> Signed-off-by: Shangming Cai <[email protected]> Signed-off-by: Chang Su <[email protected]> Signed-off-by: Noa Neria <[email protected]> Co-authored-by: Estrella-xx <[email protected]> Co-authored-by: McZyWu <[email protected]> Co-authored-by: amote-i <[email protected]> Co-authored-by: longxin9715 <[email protected]> Co-authored-by: j30065060 <[email protected]> Co-authored-by: jianzhao-xu <[email protected]> Co-authored-by: Jianzhao Xu <[email protected]> Co-authored-by: iridiumine <[email protected]> Co-authored-by: chx96642264 <[email protected]> Co-authored-by: chx96642264 <[email protected]> Co-authored-by: heziiop <[email protected]> Co-authored-by: cen121212 <[email protected]> Co-authored-by: Bingxu Chen <[email protected]> Co-authored-by: Xiaoyu Zhang <[email protected]> Co-authored-by: yang1002378395-cmyk <[email protected]> Co-authored-by: Mick <[email protected]> Co-authored-by: Bi Xue <[email protected]> Co-authored-by: huangtingwei <[email protected]> Co-authored-by: Lianmin Zheng <[email protected]> Co-authored-by: Baizhou Zhang <[email protected]> Co-authored-by: Muqi Li <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Qiaolin Yu <[email protected]> Co-authored-by: narutolhy <[email protected]> Co-authored-by: Ethan (Yusheng) Su <[email protected]> Co-authored-by: zhangxiaolei <[email protected]> Co-authored-by: Vladislav Nosivskoy <[email protected]> Co-authored-by: Trevor Morris <[email protected]> Co-authored-by: Eitan Turok <[email protected]> Co-authored-by: Fengyuan Yu <[email protected]> Co-authored-by: Fengyuan Yu <[email protected]> Co-authored-by: Adarsh Shirawalmath <[email protected]> Co-authored-by: Yuhao Yang <[email protected]> Co-authored-by: Liangsheng Yin <[email protected]> Co-authored-by: Jianying <[email protected]> Co-authored-by: jianyingzhu <[email protected]> Co-authored-by: Kangyan-Zhou <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: Jacob0226 <[email protected]> Co-authored-by: Aditya Sharma <[email protected]> Co-authored-by: Yuan Luo <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: Артем Савкин <[email protected]> Co-authored-by: Tamir Baydasov <[email protected]> Co-authored-by: Shu Wang <[email protected]> Co-authored-by: eigen <[email protected]> Co-authored-by: Avery Huang <[email protected]> Co-authored-by: jacky.cheng <[email protected]> Co-authored-by: HaiShaw <[email protected]> Co-authored-by: luoyuan.luo <[email protected]> Co-authored-by: Shangming Cai <[email protected]> Co-authored-by: Junrong Lin <[email protected]> Co-authored-by: Simon (Jiyou) Li <[email protected]> Co-authored-by: 继优 <[email protected]> Co-authored-by: shuwenn <[email protected]> Co-authored-by: psaab <[email protected]> Co-authored-by: hnyls2002 <[email protected]> Co-authored-by: Hanlin Bi <[email protected]> Co-authored-by: wili <[email protected]> Co-authored-by: saatwiknagpal <[email protected]> Co-authored-by: Mohammad Miadh Angkad <[email protected]> Co-authored-by: wan4ch <[email protected]> Co-authored-by: Feng Su <[email protected]> Co-authored-by: Ying Sheng <[email protected]> Co-authored-by: Polisetty V R K Jyothendra Varma <[email protected]> Co-authored-by: Ziang Li <[email protected]> Co-authored-by: Aishwarya Ramasethu <[email protected]> Co-authored-by: Ma Mingfei <[email protected]> Co-authored-by: blzheng <[email protected]> Co-authored-by: kk <[email protected]> Co-authored-by: wunhuang <[email protected]> Co-authored-by: Michelle Wu <[email protected]> Co-authored-by: wuxue (C) <[email protected]> Co-authored-by: Hubert Lu <[email protected]> Co-authored-by: strgrb <[email protected]> Co-authored-by: LiYomi <[email protected]> Co-authored-by: mengxiancheng03 <[email protected]> Co-authored-by: GXIN <[email protected]> Co-authored-by: 高鑫 <[email protected]> Co-authored-by: heziiop <[email protected]> Co-authored-by: xieminghe1 <[email protected]> Co-authored-by: undefined <[email protected]> Co-authored-by: Makcum888e <[email protected]> Co-authored-by: yuefeng Wu <[email protected]> Co-authored-by: Yuxuan Zhang <[email protected]> Co-authored-by: Vedant V Jhaveri <[email protected]> Co-authored-by: ronnie_zheng <[email protected]> Co-authored-by: Zhai Feiyue <[email protected]> Co-authored-by: jhchouuu <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: DarkSharpness <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: Lewis <[email protected]> Co-authored-by: 百麒 <[email protected]> Co-authored-by: Jincong Chen <[email protected]> Co-authored-by: xiazhahe <[email protected]> Co-authored-by: Thomas Wang <[email protected]> Co-authored-by: Ke Bao <[email protected]> Co-authored-by: xiaoqi <[email protected]> Co-authored-by: xiaoqi.31 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: weireweire <[email protected]> Co-authored-by: Weiliangl User <[email protected]> Co-authored-by: JD <[email protected]> Co-authored-by: Zhangheng <[email protected]> Co-authored-by: Michael <[email protected]> Co-authored-by: Yilong Zhao <[email protected]> Co-authored-by: Johnsonms <[email protected]> Co-authored-by: Brayden Zhong <[email protected]> Co-authored-by: Chang Su <[email protected]> Co-authored-by: KnightLTC <[email protected]> Co-authored-by: Douglas Yang <[email protected]> Co-authored-by: Karan Bansal <[email protected]> Co-authored-by: karanb192 <[email protected]> Co-authored-by: R0CKSTAR <[email protected]> Co-authored-by: sglang-bot <[email protected]> Co-authored-by: sglang-bot <[email protected]> Co-authored-by: Xinyuan Tong <[email protected]> Co-authored-by: sbeurnier <[email protected]> Co-authored-by: YC Yen-Ching Tseng <[email protected]> Co-authored-by: Wenyao Gao <[email protected]> Co-authored-by: Alex Nails <[email protected]> Co-authored-by: Zhiqiang Xie <[email protected]> Co-authored-by: yudian0504 <[email protected]> Co-authored-by: yunkchen <[email protected]> Co-authored-by: wduan-hai <[email protected]> Co-authored-by: Cherry_ming <[email protected]> Co-authored-by: Ratish P <[email protected]> Co-authored-by: YAMY <[email protected]> Co-authored-by: Alison Shao <[email protected]> Co-authored-by: ishandhanani <[email protected]> Co-authored-by: Derek Yu <[email protected]> Co-authored-by: Noa Neria <[email protected]> Co-authored-by: Hanlin Bi <[email protected]> Co-authored-by: Prozac614 <[email protected]> Co-authored-by: David Cheung <[email protected]> Co-authored-by: Mook <[email protected]> Co-authored-by: Khoa Pham <[email protected]> Co-authored-by: foraxe <[email protected]> Co-authored-by: yunzhi <[email protected]> Co-authored-by: DarkSharpness <[email protected]> Co-authored-by: Todobe <[email protected]> Co-authored-by: ori <[email protected]> Co-authored-by: Thomas <[email protected]> Co-authored-by: zhangshuai (S) <[email protected]> Co-authored-by: lviy <[email protected]> Co-authored-by: Tingwei Huang <[email protected]> Co-authored-by: Yuzhen Zhou <[email protected]> Co-authored-by: Ricardo-M-L <[email protected]> Co-authored-by: Kelon <[email protected]> Co-authored-by: cen121212 <[email protected]> Co-authored-by: silencejade <[email protected]> Co-authored-by: shadowxz109 <[email protected]> Co-authored-by: Henson-Zh-Ali <[email protected]> Co-authored-by: Rain Jiang <[email protected]> Co-authored-by: David Wang <[email protected]> Co-authored-by: Jian Chen <[email protected]> Co-authored-by: Zhijian Liu <[email protected]> Co-authored-by: Richard Gong <[email protected]> Co-authored-by: yilian49 <[email protected]> Co-authored-by: xm:D <[email protected]> Co-authored-by: Thomas Wang <[email protected]>
caitengwei
pushed a commit
to caitengwei/sglang
that referenced
this pull request
Jun 1, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
urlopen,requests.getfor dataset/image downloads) to prevent silent CI hangsmax-parallelforstage-b-test-1-gpu-small(5090) andstage-b-test-2-gpu-large(2-gpu-h100), matching the existing H100 pattern:set-parallelstep to determine full vs throttled once, then set all valuesTest plan