[MFM] Merge changes from vllm-project/vllm main#28

Merged

tjtanaa merged 30 commits intoEmbeddedLLM:port-rocm-cpa-creditfrom vllm-project:main

Jan 27, 2025

+3,639-526

Commits on Jan 24, 2025

[Misc] Use VisionArena Dataset for VLM Benchmarking (#12389 )
ywang96
authored
[ci/build] fix wheel size check (#12396 )
youkaichao
authored
[Hardware][Gaudi][Doc] Add missing step in setup instructions (#12382 )
MohitIntel
authored
[ci/build] sync default value for wheel size (#12398 )
youkaichao
authored
[Misc] Enable proxy support in benchmark script (#12356 )
jsato8094
authored
[Bugfix][Kernel] Fix CUDA 11.8 being broken by FA3 build (#12375 )
LucasWilkinson
authored
[Misc] Remove deprecated code (#12383 )
DarkLight1337
authored
[Bugfix][Kernel] FA3 Fix - RuntimeError: This flash attention build only supports pack_gqa (for build size reasons). (#12405 )
LucasWilkinson
authored

Commits on Jan 26, 2025

Commits on Jan 27, 2025