Skip to content

Conversation

@sfallah
Copy link
Owner

@sfallah sfallah commented Dec 11, 2025

Quick and dirty test script comparing the results of Qwen2.5-VL and DeepSeek-OCR.

quick and dirty test script comparing results of Qwen2.5-VL vs DeepSeek-OCR
@sfallah
Copy link
Owner Author

sfallah commented Dec 11, 2025

@bluebread
Some updates for you:

  1. I’ve made the model more stable by simplifying the dynamic resolution logic and limiting it to the base and large image sizes.
  2. This PR now includes a very rudimentary test script.
  3. I attempted to integrate the reference implementation from Dogacel/DeepSeek-OCR-Metal-MPS (https://huggingface.co/Dogacel/DeepSeek-OCR-Metal-MPS), but there is an issue—even though it already runs in a separate virtualenv on my local machine. I’ll probably add the mlx-vlm implementation later today, which can run on both macOS and CUDA.

bluebread pushed a commit to bluebread/llama.cpp that referenced this pull request Dec 14, 2025
…rg#17764)

* Squashed commit of the following:

commit b3c6bf4
Author: Abhijit Ramesh <[email protected]>
Date:   Mon Dec 1 18:29:00 2025 -0800

    ggml webgpu: fix xielu parameter passing (sfallah#11)

    The XIELU operation was incorrectly using static_cast to convert
    float parameters to uint32_t, which converted numeric values instead
    of preserving IEEE 754 bit patterns. This caused incorrect values
    to be interpreted by the GPU shader.

    * Use reinterpret_cast to preserve float bit patterns when passing
      through uint32_t params buffer
    * Update WGSL shader parameter types from u32 to f32
    * Re-enable XIELU support (was disabled due to numerical issues)

    Fixes NMSE test failures for XIELU operation on WebGPU backend.

commit 5ca9b5e
Author: neha-ha <[email protected]>
Date:   Tue Nov 18 12:17:00 2025 -0800

    Refactored pipelines and workgroup calculations (sfallah#10)

    * refactored pipelines

    * refactored workgroup calculation

    * removed commented out block of prior maps

    * Clean up ceiling division pattern

    ---------

    Co-authored-by: Neha Abbas <[email protected]>
    Co-authored-by: Reese Levine <[email protected]>

Author: James Contini <[email protected]>
Date:   Wed Oct 29 23:13:06 2025 -0700

    formatted embed wgsl and ggml-webgpu.cpp

commit e1f6bae
Author: James Contini <[email protected]>
Date:   Wed Oct 29 23:08:37 2025 -0700

    implemented REPL_Template support and removed bug in unary operators kernel

commit 8c70b8f
Author: James Contini <[email protected]>
Date:   Wed Oct 15 16:14:20 2025 -0700

    responded and dealt with PR comments

commit f9282c6
Author: James Contini <[email protected]>
Date:   Sun Oct 12 13:41:41 2025 -0700

    removed unnecesarry checking if node->src[1] exists for unary operators

commit 4cf28d7
Author: James Contini <[email protected]>
Date:   Sun Oct 12 13:32:45 2025 -0700

    All operators (inlcluding xielu) working

commit 74c6add
Author: James Contini <[email protected]>
Date:   Fri Oct 10 13:16:48 2025 -0700

    fixed autoconfig

commit 3627499
Author: James Contini <[email protected]>
Date:   Fri Oct 10 13:10:46 2025 -0700

    removed vestigial files

commit cb08583
Author: James Contini <[email protected]>
Date:   Fri Oct 10 12:59:32 2025 -0700

    abides by editor-config

commit 5360e28
Author: James Contini <[email protected]>
Date:   Fri Oct 10 12:45:57 2025 -0700

    rms_norm double declaration bug atoned

commit 7b09baa
Merge: 8a6ec84 74b8fc1
Author: James Contini <[email protected]>
Date:   Fri Oct 10 11:50:03 2025 -0700

    resolving merge conflicts

commit 8a6ec84
Author: James Contini <[email protected]>
Date:   Wed Oct 8 18:06:47 2025 -0700

    unary operators pass ggml tests

commit c3ae382
Author: James Contini <[email protected]>
Date:   Wed Oct 1 16:22:40 2025 -0700

    neg passes backend test

commit aa1c9b2
Author: James Contini <[email protected]>
Date:   Tue Sep 30 23:55:27 2025 -0700

    neg f16xf32xip builds and runs, havent actually ran a model that uses neg kernel yet though

Co-authored-by: James Contini <[email protected]>
Co-authored-by: Neha Abbas <[email protected]>
Co-authored-by: Abhijit Ramesh <[email protected]>

* Remove extra code and format

* Add ops documentation (finally)

* Update ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py

Co-authored-by: Sigbjørn Skjæret <[email protected]>

---------

Co-authored-by: James Contini <[email protected]>
Co-authored-by: Neha Abbas <[email protected]>
Co-authored-by: Abhijit Ramesh <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
@sfallah sfallah marked this pull request as ready for review December 14, 2025 15:37
@sfallah sfallah merged commit 3fc61d4 into sf/deepseek-ocr Dec 14, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants