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: ecbbd1590f85ede480352024def6238729eb90d4
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: 26a83d6fdb78185305413d5baa2b0ab05c5f73f9
Choose a head ref
  • 20 commits
  • 45 files changed
  • 18 contributors

Commits on Aug 18, 2025

  1. [None] [feat] Support accurate device iter time (#6906) 

    Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
    @kaiyux
    kaiyux authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    e88cb92 View commit details
    Browse the repository at this point in the history

  2. [TRTLLM-7030][fix] uppercase def value in pd-config (#6981) 

    Signed-off-by: ShiXiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
    @Shixiaowei02
    Shixiaowei02 authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    5ec15b9 View commit details
    Browse the repository at this point in the history

  3. [None] [fix] Fix the macro name (#6983) 

    Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
    @ChristinaZ
    ChristinaZ authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    55f4f2d View commit details
    Browse the repository at this point in the history

  4. [None][infra] Waive failed tests on main 0818 (#6992) 

    Signed-off-by: qqiao <qqiao@nvidia.com>
    @EmmaQiaoCh
    EmmaQiaoCh authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    69ff32f View commit details
    Browse the repository at this point in the history

  5. [None][chore] Remove duplicate test waives (#6998) 

    Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
    @yiqingy0
    yiqingy0 authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    1ce2354 View commit details
    Browse the repository at this point in the history

  6. [None][fix] Clean up linking to CUDA stub libraries in build_wheel.py (… 

    …#6823)

Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Co-authored-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
    @MartinMarciniszyn @Linda-Stadter
    MartinMarciniszyn and Linda-Stadter authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    425dad0 View commit details
    Browse the repository at this point in the history

  7. [None][infra] Cherry-pick #6836 from main branch and improve SSH conn… 

    …ection (#6971) (#7005)

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
    @chzblych @ZhanruiSunCh
    chzblych and ZhanruiSunCh authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    d1d17db View commit details
    Browse the repository at this point in the history

  8. [TRTLLM-7158][feat] Introduce sampler options in trtllm bench (#6855) 

    Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
    @dcampora
    dcampora authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    d16af87 View commit details
    Browse the repository at this point in the history

  9. [None][infra] Enable accuracy test for mtp and chunked prefill (#6314) 

    Signed-off-by: leslie-fang25 <leslief@nvidia.com>
    @leslie-fang25
    leslie-fang25 authored Aug 18, 2025
    Configuration menu
    Copy the full SHA
    e76e5c6 View commit details
    Browse the repository at this point in the history

Commits on Aug 19, 2025

  1. [None][autodeploy] Doc: fix link path in trtllm bench doc (#7007) 

    Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
    @Fridah-nv
    Fridah-nv authored Aug 19, 2025
    Configuration menu
    Copy the full SHA
    97ba0eb View commit details
    Browse the repository at this point in the history

  2. [https://nvbugs/5371480][fix] Enable test_phi3_small_8k (#6938) 

    Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
    @Wanli-Jiang
    Wanli-Jiang authored Aug 19, 2025
    Configuration menu
    Copy the full SHA
    dabebb2 View commit details
    Browse the repository at this point in the history

  3. [TRTLLM-7014][chore] Add accuracy test for ctx and gen workers with d… 

    …ifferent models (#6741)

Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
    @reasonsolo
    reasonsolo authored Aug 19, 2025
    Configuration menu
    Copy the full SHA
    71e28ea View commit details
    Browse the repository at this point in the history

  4. [None][refactor] Refactor Torch Compile Backend, MoeLoadBalancer and … 

    …warmup Logic (#6615)

Signed-off-by: yizhang-nv <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
    @yizhang-nv
    yizhang-nv authored Aug 19, 2025
    Configuration menu
    Copy the full SHA
    a15af87 View commit details
    Browse the repository at this point in the history

  5. [None] [infra] stricter coderabbit pr title generation instructions (#… 

    …6918)

Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
    @venkywonka
    venkywonka authored Aug 19, 2025
    Configuration menu
    Copy the full SHA
    06911c0 View commit details
    Browse the repository at this point in the history

  6. [TRTLLM-6960][fix] enable scaled_mm tests (#6936) 

    Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
    @dc3671
    dc3671 authored Aug 19, 2025
    Configuration menu
    Copy the full SHA
    2bb90ba View commit details
    Browse the repository at this point in the history

  7. add llmapi trt flow test case with cuda graph and generate logits 

    Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
    @crazydemo
    crazydemo committed Aug 19, 2025
    Configuration menu
    Copy the full SHA
    c49f0f1 View commit details
    Browse the repository at this point in the history

  8. add llmapi logprobs test with trt flow 

    Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
    @crazydemo
    crazydemo committed Aug 19, 2025
    Configuration menu
    Copy the full SHA
    e395958 View commit details
    Browse the repository at this point in the history

  9. add llmapi trt flow phi-4-mini-instruct acc test 

    Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
    @crazydemo
    crazydemo committed Aug 19, 2025
    Configuration menu
    Copy the full SHA
    117bd93 View commit details
    Browse the repository at this point in the history

  10. add nemo 12b base test cases 

    Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
    @crazydemo
    crazydemo committed Aug 19, 2025
    Configuration menu
    Copy the full SHA
    ead824e View commit details
    Browse the repository at this point in the history

  11. fix invalid test name 

    Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
    @crazydemo
    crazydemo committed Aug 19, 2025
    Configuration menu
    Copy the full SHA
    26a83d6 View commit details
    Browse the repository at this point in the history
Loading