Repository navigation

Commits

Commits on May 7, 2026
- [ROCm] Enable SimpleCPUOffloadConnector on ROCm (#40549)
  
  hongxiayang
  and
  tjtanaa
  authored
  20cac26
Commits on Mar 30, 2026
- [ROCm][Bugfix] fix exception related to trust_remote_code for MiniMax-M2.1-MXFP4 (#37698)
  
  hongxiayang
  and
  Hongxia Yang
  authored
  dbdd9ae
Commits on Mar 27, 2026
- [ROCm][Documentation] update quickstart and installation to include rocm nightly docker tips (#38367)
  
  hongxiayang
  and
  Hongxia Yang
  authored
  83a4df0
Commits on Mar 19, 2026
- [ROCm] issue management - request information for bug issues on ROCm (#37009)
  hongxiayang
  authored
  e3126cd
Commits on Mar 2, 2026
- [ROCm] add amd-quark package in requirements for rocm to use quantized models (#35658)
  
  hongxiayang
  and
  Hongxia Yang
  authored
  f26650d
Commits on Feb 18, 2026
- [BugFix] [Build] fix string literals comparison in indexer_k_quant_and_cache calling site (#34653)
  
  hongxiayang
  and
  Hongxia Yang
  authored
  4a00a51
Commits on Feb 9, 2026
- [ROCm] update triton branch to support gpt-oss models for gfx11xx devices (#34032)
  hongxiayang
  authored
  4d39650
Commits on Jan 14, 2026
- AMD CI Test - unskip moe_sum test and moe_align_block_size tests (#32039)
  hongxiayang
  authored
  048bb59
Commits on Nov 21, 2025
- [ROCm] Fix for import when building with upstream triton for gfx1100 for gpt-oss serving (#29127)
  hongxiayang
  authored
  3f5f36d
Commits on Aug 26, 2025
- [ROCm] Starting to add AMD code reviewers for ROCm components (#23496)
  hongxiayang
  authored
  1fdc732
Commits on May 28, 2025
- [Bugfix][ROCm] fix the power of 2 exception from triton_unified_attention.py when running llama4 models and unit test fix (#18100)
  
  hongxiayang
  and
  tjtanaa
  authored
  269d901
Commits on May 7, 2025
- [ROCm] fix num_stages for default moe config to avoid triton OutOfResource error (#17744)
  hongxiayang
  authored
  ed3a1d2
Commits on May 1, 2025
Commits on Feb 4, 2025
- [AMD][ROCm] Enable DeepSeek model on ROCm (#12662)
  
  hongxiayang
  and
  mawong-amd
  authored
  c36ac98
Commits on Jan 21, 2025
- [Documentation][AMD] Add information about prebuilt ROCm vLLM docker for perf validation purpose (#12281)
  hongxiayang
  authored
  09ccc9c
Commits on Jan 18, 2025
- [AMD][CI/Build][Bugfix] use pytorch stale wheel (#12172)
  hongxiayang
  authored
  c09503d
Commits on Sep 25, 2024
- [CI/Build][Bugfix][Doc][ROCm] CI fix and doc update after ROCm 6.2 upgrade (#8777)
  hongxiayang
  authored
  1c04644
Commits on Sep 24, 2024
- [Hardware][AMD] ROCm6.2 upgrade (#8674)
  hongxiayang
  authored
  530821d
Commits on Jul 24, 2024
- [Doc][AMD][ROCm]Added tips to refer to mi300x tuning guide for mi300x users (#6754)
  hongxiayang
  authored
  d88c458
Commits on Jul 17, 2024
- [ROCm] Cleanup Dockerfile and remove outdated patch (#6482)
  hongxiayang
  authored
  1038388
Commits on Jul 12, 2024
- [ROCm][AMD] unify CUDA_VISIBLE_DEVICES usage in cuda/rocm (#6352)
  hongxiayang
  authored
  b6c16cf
Commits on Jun 19, 2024
- [Bugfix][CI/Build][AMD][ROCm]Fixed the cmake build bug which generate garbage on certain devices (#5641)
  hongxiayang
  authored
  f758aed
Commits on Jun 8, 2024
- [ROCm][AMD] Use pytorch sdpa math backend to do naive attention (#4965)
  hongxiayang
  authored
  c96fc06
Commits on May 16, 2024
- [ROCm][AMD][Bugfix] adding a missing triton autotune config (#4845)
  hongxiayang
  authored
  b5853f9
Commits on Apr 27, 2024
- [ROCm][Hardware][AMD] Enable group query attention for triton FA (#4406)
  hongxiayang
  authored
  18d23f6
Commits on Apr 26, 2024
- [ROCm][Hardware][AMD][Doc] Documentation update for ROCm (#4376)
  
  hongxiayang
  and
  WoosukKwon
  authored
  cf29b7e
Commits on Apr 22, 2024
- [AMD][Hardware][Misc][Bugfix] xformer cleanup and light navi logic and CI fixes and refactoring (#4129)
  hongxiayang
  authored
  95e5b08
Commits on Mar 29, 2024
- [ROCm][Bugfix] Fixed several bugs related to rccl path and attention selector logic (#3699)
  hongxiayang
  authored
  9765b5c
Commits on Mar 5, 2024
- [ROCm] enable cupy in order to enable cudagraph mode for AMD GPUs (#3123)
  
  hongxiayang
  and
  lcskrishna
  authored
  05af6da
Commits on Feb 15, 2024
- [ROCm] Dockerfile fix for flash-attention build (#2885)
  hongxiayang
  authored
  5255d99
Commits on Feb 11, 2024
- [ROCm] support Radeon™ 7900 series (gfx1100) without using flash-attention (#2768)
  hongxiayang
  authored
  0580aab
Commits on Feb 7, 2024
- [ROCm] Fix build problem resulted from previous commit related to FP8 kv-cache support (#2790)
  hongxiayang
  authored
  c81dddb
Commits on Feb 5, 2024
- [ROCm] Fix some kernels failed unit tests (#2498)
  hongxiayang
  authored
  56f738a

Branch selector

User selector

Datepicker

Commit history

Commits on May 7, 2026

Commits on Mar 30, 2026

Commits on Mar 27, 2026

Commits on Mar 19, 2026

Commits on Mar 2, 2026

Commits on Feb 18, 2026

Commits on Feb 9, 2026

Commits on Jan 14, 2026

Commits on Nov 21, 2025

Commits on Aug 26, 2025

Commits on May 28, 2025

Commits on May 7, 2025

Commits on May 1, 2025

Commits on Feb 4, 2025

Commits on Jan 21, 2025

Commits on Jan 18, 2025

Commits on Sep 25, 2024

Commits on Sep 24, 2024

Commits on Jul 24, 2024

Commits on Jul 17, 2024

Commits on Jul 12, 2024

Commits on Jun 19, 2024

Commits on Jun 8, 2024

Commits on May 16, 2024

Commits on Apr 27, 2024

Commits on Apr 26, 2024

Commits on Apr 22, 2024

Commits on Mar 29, 2024

Commits on Mar 5, 2024

Commits on Feb 15, 2024

Commits on Feb 11, 2024

Commits on Feb 7, 2024

Commits on Feb 5, 2024