1. 07 May, 2025 2 commits
  2. 24 Apr, 2025 1 commit
  3. 23 Apr, 2025 1 commit
  4. 01 Apr, 2025 1 commit
  5. 31 Mar, 2025 1 commit
  6. 26 Mar, 2025 1 commit
  7. 24 Mar, 2025 1 commit
  8. 15 Mar, 2025 1 commit
  9. 18 Feb, 2025 1 commit
  10. 05 Feb, 2025 1 commit
  11. 04 Feb, 2025 1 commit
  12. 03 Feb, 2025 1 commit
  13. 02 Feb, 2025 1 commit
    • Russell Bryant's avatar
      [Misc] Add SPDX-License-Identifier headers to python source files (#12628) · e489ad7a
      Russell Bryant authored
      - **Add SPDX license headers to python source files**
      - **Check for SPDX headers using pre-commit**
      
      commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
      Author: Russell Bryant <rbryant@redhat.com>
      Date:   Fri Jan 31 14:18:24 2025 -0500
      
          Add SPDX license headers to python source files
          
      This commit adds SPDX license headers to python source files as
      recommended to
      the project by the Linux Foundation. These headers provide a concise way
      that is
      both human and machine readable for communicating license information
      for each
      source file. It helps avoid any ambiguity about the license of the code
      and can
          also be easily used by tools to help manage license compliance.
          
      The Linux Foundation runs license scans against the codebase to help
      ensure
          we are in compliance with the licenses of the code we use, including
      dependencies. Having these headers in place helps that tool do its job.
          
          More information can be found on the SPDX site:
          
          - https://spdx.dev/learn/handling-license-info/
      
      Signed-off-by: default avatarRussell Bryant <rbryant@redhat.com>
      
      commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
      Author: Russell Bryant <rbryant@redhat.com>
      Date:   Fri Jan 31 14:36:32 2025 -0500
      
          Check for SPDX headers using pre-commit
      Signed-off-by: default avatarRussell Bryant <rbryant@redhat.com>
      
      ---------
      Signed-off-by: default avatarRussell Bryant <rbryant@redhat.com>
      e489ad7a
  14. 14 Jan, 2025 1 commit
  15. 24 Dec, 2024 1 commit
  16. 11 Dec, 2024 1 commit
  17. 07 Dec, 2024 1 commit
  18. 01 Dec, 2024 1 commit
  19. 04 Oct, 2024 1 commit
  20. 16 Sep, 2024 1 commit
  21. 10 Sep, 2024 1 commit
  22. 27 Aug, 2024 1 commit
  23. 22 Aug, 2024 1 commit
  24. 21 Aug, 2024 1 commit
  25. 06 Aug, 2024 1 commit
  26. 24 Apr, 2024 1 commit
    • Philipp Moritz's avatar
      [Kernel] FP8 support for MoE kernel / Mixtral (#4244) · eace8bf0
      Philipp Moritz authored
      This PR is the first step towards fixing https://github.com/vllm-project/vllm/pull/3208
      
      It implements dynamic per-tensor scaling (see https://github.com/vllm-project/vllm/pull/4118), so users do not need to compute activation scales on a calibration dataset and they also don't need to convert their model checkpoints. It is enough to specify the `quantization="fp8"` argument. You can try out the PR like this:
      
      ```python
      from vllm import LLM, SamplingParams
      
      prompts = [
          "Hello, my name is",
          "The president of the United States is",
          "The capital of France is",
          "The future of AI is",
      ]
      sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
      
      llm = LLM(model="mistralai/Mixtral-8x7B-Instruct-v0.1", tensor_parallel_size=2, quantization="fp8")
      
      outputs = llm.generate(prompts, sampling_params)
      
      # Print the outputs.
      for output in outputs:
          prompt = output.prompt
          generated_text = output.outputs[0].text
          print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
      ```
      
      **Performance**: For this PR, the focus is on making the code clean (while still trying to get reasonable performance), there is a bunch of optimizations that we will submit as a follow up PR that significantly improve the performance (similar to the numbers in https://github.com/vllm-project/vllm/pull/3954). With this PR, the results are as follows:
      
      <img width="725" alt="Screenshot 2024-04-21 at 1 31 50 PM" src="https://github.com/vllm-project/vllm/assets/113316/d8fe1118-07a0-4d4e-8530-37a77d465a03">
      
      
      **Accuracy**: The accuracy with this PR on MMLU on `mistralai/Mixtral-8x7B-v0.1` is as follows:
      
      ```
      |      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
      |------------------|-------|------|-----:|------|-----:|---|-----:|
      |mmlu              |N/A    |none  |     0|acc   |0.7018|±  |0.0036|
      | - humanities     |N/A    |none  |     5|acc   |0.6472|±  |0.0065|
      | - other          |N/A    |none  |     5|acc   |0.7673|±  |0.0072|
      | - social_sciences|N/A    |none  |     5|acc   |0.8099|±  |0.0070|
      | - stem           |N/A    |none  |     5|acc   |0.6131|±  |0.0083|
      ```
      this compares favorably with the fp16 results which are
      ```
      |      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
      |------------------|-------|------|-----:|------|-----:|---|-----:|
      |mmlu              |N/A    |none  |     0|acc   |0.7020|±  |0.1313|
      | - humanities     |N/A    |none  |     5|acc   |0.6425|±  |0.1349|
      | - other          |N/A    |none  |     5|acc   |0.7744|±  |0.1038|
      | - social_sciences|N/A    |none  |     5|acc   |0.8131|±  |0.0695|
      | - stem           |N/A    |none  |     5|acc   |0.6108|±  |0.1383|
      ```
      
      Happy hacking!
      eace8bf0
  27. 16 Apr, 2024 1 commit