A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 20:15 UTC
main
haosdent committed 6 months ago
[UT][XPU] fix test_parallel_sampling due to global random state (#42388)
liuzhenwei committed 6 months ago
[CI] Move DockerHub and PyPI publish steps to end of release pipeline (#42355)
Kevin H. Luu committed 6 months ago
[CI] Migrate remaining B200 jobs to b200-k8s with test fixes (#42387)
Kevin H. Luu committed 6 months ago
[Bugfix] Fix empty channel/recipient in harmony for /v1/responses (#35540)
chazen committed 6 months ago
amitz-nv committed 6 months ago
[CI] Migrate more B200 jobs to b200-k8s queue (#42356)
Kevin H. Luu committed 6 months ago
[Frontend] Consolidate Speech to Text entrypoints. (#42370)
wang.yuqi committed 6 months ago
[XPU] update dp rank w/o env-var isolation (#39856)
liuzhenwei committed 6 months ago
[Bugfix][Performance Improvement] Improve penalties triton kernel performance (#40657)
Lucas Kabela committed 6 months ago
Implement custom dataset class for ASR benchmarking (#41576)
Yasmin Moslem committed 6 months ago
[Fix] Gemma4 Mixed-Resolution Image Co-Batching Crash (#42217)
ZiTian Zhao committed 6 months ago
[Bugifx] [Qwen3CoderTool] Restore supports_required_and_named for required tool_choice (#42292)
Chauncey committed 6 months ago
Add VLLM_USE_SPINLOOP_EXT to use more efficient busy polling (#36517)
pschlan-amd committed 6 months ago
[Model Runner V2] Bug fix: logprob dtype int64/int32 issue (#41761)
Wentao Ye committed 6 months ago
[Perf][1/n] Eliminate various GPU<->CPU syncs (#41429)
Nick Hill committed 6 months ago
[Bugfix] Fix DSV4 swiglu_limit on marlin backend (#42287)
Jee Jee Li committed 6 months ago
[CI] Consolidate Speech to Text tests (#42274)
wang.yuqi committed 6 months ago
[BugFix] Prevent orphaned process on NCCL destroy (#39846)
Jeffrey Wang committed 6 months ago
[CI] Add tests/parser to CI coverage (#41877)
Flora Feng committed 6 months ago