Commits

Branch selector

main

User selector

huydhn

All time

Commit history

Commits on Jul 27, 2025

• Handle non-serializable objects in vllm bench (#21665)

  huydhn

  authored
  971948bView commit details

  Copy full SHA for 971948b

  Browse repository at this point

Commits on Jul 26, 2025

• [Take 2] Correctly kill vLLM processes after benchmarks (#21646)

  Show description for e98def4
  huydhn

  authored
  e98def4View commit details

  Copy full SHA for e98def4

  Browse repository at this point

• Correctly kill vLLM processes after finishing serving benchmarks (#21641)

  Show description for a55c950
  huydhn

  authored
  a55c950View commit details

  Copy full SHA for a55c950

  Browse repository at this point

Commits on Jul 21, 2025

• Add the instruction to run e2e validation manually before release (#21023)

  Show description for 940af1f
  huydhn

  authored
  940af1fView commit details

  Copy full SHA for 940af1f

  Browse repository at this point

Commits on Jul 19, 2025

• Fix a couple of Voxtral tests (#21218)

  Show description for cf8cc32
  huydhn

  authored
  cf8cc32View commit details

  Copy full SHA for cf8cc32

  Browse repository at this point

Commits on Jun 29, 2025

• Fix cuda_archs_loose_intersection when handling sm_*a (#20207)

  Show description for 6c9837a
  huydhn

  authored
  6c9837aView commit details

  Copy full SHA for 6c9837a

  Browse repository at this point

Commits on Jun 17, 2025

• Add a doc on how to update PyTorch version (#19705)

  huydhn

  authored
  c48c6c4View commit details

  Copy full SHA for c48c6c4

  Browse repository at this point

Commits on Jun 14, 2025

• Only build CUTLASS MoE kernels on Hopper (#19648)

  huydhn

  authored
  bc956b3View commit details

  Copy full SHA for bc956b3

  Browse repository at this point

Commits on Jun 5, 2025

• Handle non-serializable objects when dumping benchmark results (#19114)

  huydhn

  authored
  0678b52View commit details

  Copy full SHA for 0678b52

  Browse repository at this point

Commits on May 23, 2025

• Use prebuilt FlashInfer x86_64 PyTorch 2.7 CUDA 12.8 wheel for CI (#18537)

  Show description for 1645b60
  huydhn

  authored
  1645b60View commit details

  Copy full SHA for 1645b60

  Browse repository at this point

Commits on May 1, 2025

• Fix more broken speculative decode tests (#17450)

  Show description for b74d888
  huydhn

  authored
  b74d888View commit details

  Copy full SHA for b74d888

  Browse repository at this point

Commits on Apr 30, 2025

• Fix some speculative decode tests with tl.dot (#17371)

  Show description for 88fcf00
  huydhn

  authored
  88fcf00View commit details

  Copy full SHA for 88fcf00

  Browse repository at this point

• Update PyTorch to 2.7.0 (#16859)

  huydhn

  authored
  2c4f59aView commit details

  Copy full SHA for 2c4f59a

  Browse repository at this point

Commits on Apr 4, 2025

• [ROCm] Tweak the benchmark script to run on ROCm (#14252)

  huydhn

  authored
  092475fView commit details

  Copy full SHA for 092475f

  Browse repository at this point

Commits on Feb 24, 2025

• Fix some issues with benchmark data output (#13641)

  Show description for e7ef74e
  huydhn

  authored
  e7ef74eView commit details

  Copy full SHA for e7ef74e

  Browse repository at this point

Commits on Feb 17, 2025

• Run v1 benchmark and integrate with PyTorch OSS benchmark database (#13068)

  Show description for 4518683
  huydhn

  authored
  4518683View commit details

  Copy full SHA for 4518683

  Browse repository at this point