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 7, 02:45 UTC
main
[BugFix] avoid infinite loop with VLLM_PORT and get_open_ports_list (#36191)
Walter Beller-Morales committed 8 months ago
[Security] Respect user trust_remote_code setting in NemotronVL and KimiK25 (#36192)
Russell Bryant committed 8 months ago
[Bugfix] Fix misleading context length error messages (#36197)
Ajay Anubolu committed 8 months ago
[Bugfix] Fix inner_dp_world initialization order for multi-node TP (#35892)
Yongye Zhu committed 8 months ago
[Frontend][Core] Add shutdown timeout - allowing in-flight requests to finish (#34730)
Mark McLoughlin committed 8 months ago
perf: add __slots__ to KVCacheBlock (#36164)
cong-or committed 8 months ago
docs: fix wrong cc in int8.md (#36209)
Xiang Shi committed 8 months ago
[CI] Fix bge-m3 similarity reference values after *Defination* typo fix (#36208)
Andreas Karatzas committed 8 months ago
[BugFix] Fix engine hanging after KV cache initialization failure (#35478)
Shiyan Deng committed 8 months ago
[Feature] Add --distributed-timeout-seconds CLI option (#36047)
Shiyan Deng committed 8 months ago
[Bug] Fix a corner case in _process_simple_streaming_events (#34754)
Shiyan Deng committed 8 months ago
[Misc] Rename `group_mm_kwargs_by_modality -> group_and_batch_mm_kwargs` (#36158)
Cyrus Leung committed 8 months ago
[Bugfix] Fix simple Mistral-Small example (#36156)
Cyrus Leung committed 8 months ago
[ROCm][CI] Adding missing dependencies for Multi-modal models tests (#36177)
Andreas Karatzas committed 8 months ago
Reenable features for ROCm attention backends (#36185)
Rohan Potdar committed 8 months ago
cpu: aarch64: Upgrade OneDNN for aarch64 to add support for int8 matmul (#36147)
Nikhil Gupta committed 8 months ago
Don't fire ray compatibility webhook when PR or branch is not provided (#36088)
Jeffrey Wang committed 8 months ago
[Performance] Extract KV-cache update from TreeAttention backend (#35384)
Dor Huri committed 8 months ago
[Model Runner V2] Fix warmup for very small kvcache and/or blocksizes (#36176)
Nick Hill committed 8 months ago
[compile] Consistent compiler config for saved/loaded vllm backends. (#35810)
Zhengxu Chen committed 8 months ago