Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: NVIDIA/TensorRT-LLM
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: ee6ea78465f6227f26ab1fd9773d11b010d2f4b1
Choose a base ref
...
head repository: NVIDIA/TensorRT-LLM
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: 32458958abec6c553b3a7a27d6a01b7865f9d064
Choose a head ref
  • 15 commits
  • 26 files changed
  • 10 contributors

Commits on Sep 17, 2025

  1. [None][chore] AutoDeploy: clean up of model unit test configuration (#… 

    …7742)

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
    @lucaslie
    lucaslie authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    4c3dc89 View commit details
    Browse the repository at this point in the history

  2. [None][ci] waive test_llm_gemma_1gpu_summary_vswa (#7781) 

    Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
    @QiJune
    QiJune authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    bd7aad4 View commit details
    Browse the repository at this point in the history

  3. [https://nvbugs/5517260][fix] move scaffolding contrib module's impor… 

    …t to subdirectory (#7758)

Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
    @dc3671
    dc3671 authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    6983e8a View commit details
    Browse the repository at this point in the history

  4. [None][feat] add an example of KV cache host offloading (#7767) 

    Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
    @QiJune
    QiJune authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    3924832 View commit details
    Browse the repository at this point in the history

  5. [https://nvbugs/5485325][fix] Cherry-pick #7373: fix the CUDA graph w… 

    …armup issue when using speculative decoding (#7734)

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
    @lfr-0531 @litaotju
    lfr-0531 and litaotju authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    523a17d View commit details
    Browse the repository at this point in the history

  6. [None][ci] waive test_llama_eagle3[True-FLASHINFER-False-False-False-… 

    …False-True] (#7788)

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
    @QiJune
    QiJune authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    d3e680b View commit details
    Browse the repository at this point in the history

  7. [None][chore] Remove closed bugs (#7697) 

    Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
    @xinhe-nv
    xinhe-nv authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    7801d09 View commit details
    Browse the repository at this point in the history

  8. [None][test] add gpt oss model for trtllm perf test (#7328) 

    Signed-off-by: Ruodi Lu <ruodil@nvidia.com>
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
    @ruodil @LarryXFly
    3 people authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    e6073b3 View commit details
    Browse the repository at this point in the history

  9. [TRTLLM-7250][fix] waive block tests (#7782) 

    Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
    @xinhe-nv
    xinhe-nv authored Sep 17, 2025
    Configuration menu
    Copy the full SHA
    f918302 View commit details
    Browse the repository at this point in the history

  10. context_tp_&gen_dp_opt 

    Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
    @chuangz0
    chuangz0 committed Sep 17, 2025
    Configuration menu
    Copy the full SHA
    85fd3ef View commit details
    Browse the repository at this point in the history

  11. info->debug 

    Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
    @chuangz0
    chuangz0 committed Sep 17, 2025
    Configuration menu
    Copy the full SHA
    0804437 View commit details
    Browse the repository at this point in the history

  12. fix mla 

    Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
    @chuangz0
    chuangz0 committed Sep 17, 2025
    Configuration menu
    Copy the full SHA
    968bcd1 View commit details
    Browse the repository at this point in the history

  13. fix test 

    Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
    @chuangz0
    chuangz0 committed Sep 17, 2025
    Configuration menu
    Copy the full SHA
    4b2d103 View commit details
    Browse the repository at this point in the history

  14. async send kv cache 

    Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
    @chuangz0
    chuangz0 committed Sep 17, 2025
    Configuration menu
    Copy the full SHA
    79c992d View commit details
    Browse the repository at this point in the history

  15. remove log 

    Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
    @chuangz0
    chuangz0 committed Sep 17, 2025
    Configuration menu
    Copy the full SHA
    3245895 View commit details
    Browse the repository at this point in the history
Loading