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 9, 03:45 UTC
main
[Critical] Revert #33110 (#33500)
Cyrus Leung committed 9 months ago
[Bugfix] Fix inconsistent handling of cache reset (#33481)
Cyrus Leung committed 9 months ago
pin LMCache to v0.3.9 or greater with vLLM v0.15.0 (#33440)
Greg Pereira committed 9 months ago
[ROCm][CI] Update huggingface-hub pin (#33492)
Andreas Karatzas committed 9 months ago
[Refactor] Make Renderer an abstract class (#33479)
Cyrus Leung committed 9 months ago
fix: Add SM120 (RTX Blackwell) support for FlashInfer CUTLASS NVFP4 MoE kernels (#33417)
René Honig committed 9 months ago
[Misc] Fix flashinfer related tests (#33462)
Roy Wang committed 9 months ago
smashyalts committed 9 months ago
[Bugfix]: Fix display errors in TORCH_CHECK messages (#32942)
linhaifeng committed 9 months ago
[Misc] support collect_env for endpoint /server_info (#33246)
Xiao Yang committed 9 months ago
Update `huggingface-hub` pin for the last time before Transformers v5 (#33473)
Harry Mellor committed 9 months ago
[Refactor] Move MM data parsing outside processor (#33408)
Cyrus Leung committed 9 months ago
[Deprecation] Remove deprecated items related to pooling (#33477)
Cyrus Leung committed 9 months ago
[Bugfix] Early-reject requests with MM data longer than encode cache capacity (#33110)
YunzhuLu committed 9 months ago
Support clear mm and encoder cache (#33452)
jma99_2333 committed 9 months ago
[BugFix][Router Replay] Capture Logical Experts with EPLB (#33013)
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed 9 months ago
Luka Govedič committed 9 months ago
[Doc] Update plugin deprecation notices (#33476)
Cyrus Leung committed 9 months ago
support return prompt token ids in responses (#33378)
cmunley1 committed 9 months ago
[Misc] Replace deprecated interface seed_everything (#33474)
Roy Wang committed 9 months ago