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 5, 02:15 UTC
main
Fix #33773: Replace unconditional pandas import with PlaceholderModule (#39990)
Netanel Haber committed 7 months ago
[Docs] Update PR template to remove release notes google docs (#39982)
Simon Mo committed 7 months ago
[Bugfix] Accept **kwargs in MiniMaxM2Parser.__init__() (#39861)
Tim Messerschmidt committed 7 months ago
[XPU] use spawn multiproc method on xpu (#39671)
Xinyu Chen committed 7 months ago
Add Jina Embeddings v5 model support (fixes #38633) (#39575)
Abhijit Roy committed 7 months ago
[Bugfix] add support for 'num_attention_groups' in ModelArchConfigConvertorBase for Step3p5 (#39796)
realliujiaxu committed 7 months ago
[CPU][IBM Z][Dockefile][Docs] Fix s390x builds for torch 2.11 and update docs for s390x (#39910)
R3hankhan committed 7 months ago
[perf][cpu] Accelerate BF16 GELU with LUT impl on Arm CPUs (#37469)
Fadi Arafeh committed 7 months ago
[Bugfix] Reject empty tools array with HTTP 400 (#39780)
jigangz committed 7 months ago
[Mistral Grammar] Fix tool and reasoning parsing (#39217)
Julien Denize committed 7 months ago
[compile] Invoke split FX graph by codegen. (#38657)
Zhengxu Chen committed 7 months ago
[ROCm][FEAT] Integrate aiter gemm w8a8 ptpc (#33773)
vllmellm committed 7 months ago
[Model Runner V2][BugFix] fix num_sampled dtype for probabilistic rej… (#39951)
Giancarlo Delfin committed 7 months ago
[Quantization] - Layerwise reloading of Attention/KV quantized models (#38995)
Asaf Gardin committed 7 months ago
Update to transformers v5 (#30566)
Harry Mellor committed 7 months ago
[Model] Fix Gemma 4 token repetition by dynamic BOS injection for PT models (#39842)
Luciano Martins committed 7 months ago
Update registry for Nemotron-v3 VL Nano/Super (#39747)
Collin McCarthy committed 7 months ago
[CI Bug] fix flaky test (#39938)
Wentao Ye committed 7 months ago
[FlashAttention] Don't overwrite `flash_attn_interface.py` when installing precompiled (#39932)
Matthew Bonanni committed 7 months ago
[Bugfix][Perf] Indexer upcast WK to BF16 for fusion (#38928)
Benjamin Chislett committed 7 months ago