Pinned Loading

1. LlmTestTools LlmTestTools Public

   LLM API 性能测试工具，用于测试大语言模型的推理性能指标。

   Python 2

2. gpu-idle-saver gpu-idle-saver Public

   gpu-idle-saver

   Python 1

3. cmpunlocker2 cmpunlocker2 Public

   限制问题区域显存 62906MiB / 65024MiB 支持驱动 610.57.04 ，修改显卡显示名称为NVIDIA Tesla A100

   Shell 12 3

4. vllm vllm Public

   Forked from thomaslwang/vllm

   支持170HX 3卡PP 1M上下文，分支dsv4fpp3-v1

   Python 2

5. deepseek-v4-cmp170hx deepseek-v4-cmp170hx Public

   Forked from allover326/deepseek-v4-cmp170hx

   DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallelism, which vLLM does not support upstream.

   Python

6. vllm170hx vllm170hx Public

   vllm修改版本支持170hx ，支持3卡4卡pp 测试数据1M & 71t/s 3卡 4卡 7M &71t/s 支持dspark

   Python 6 3