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 14, 05:30 UTC
main
[MISC] fix import violations for re and triton modules (#26654)
Sungjae Lee committed about 1 year ago
Cleanup code after Python 3.10 upgrade (#26520)
Lukas Geiger committed about 1 year ago
[Model][Bugfix] fix ernie45 vl run failed from shared experts optimization (#26885)
CSWYF3634076 committed about 1 year ago
[Chore] Separate out `vllm.utils.collections` (#26990)
Cyrus Leung committed about 1 year ago
[Benchmark] Use truncation by default for pooling benchmarks (#26992)
Cyrus Leung committed about 1 year ago
[CI/Build] Fix AMD import failures in CI (#26841)
Zhewen Li committed about 1 year ago
[Hardware][CPU][PowerPC]Disable torch.compile() in toptopk sampling (#26987)
Akash kaothalkar committed about 1 year ago
[CI/Build] Update expected beam search output for Phi3V (#26978)
Cyrus Leung committed about 1 year ago
Deepseek-v3 Batch Invariant on 8xH100 (#26609)
Bram Wasti committed about 1 year ago
Vadim Gimpelson committed about 1 year ago
[Chore] Rename `utils` submodules (#26920)
Cyrus Leung committed about 1 year ago
[DOC][XPU]update feature parity with Intel GPU (#26954)
Chendi.Xue committed about 1 year ago
[BugFix] Work around graph partition x torch.compile cache issue (#26956)
Richard Zou committed about 1 year ago
[bugfix] Fix SP + PP without specifying compile size (#26955)
Angela Yi committed about 1 year ago
[BUG] Allow runai_streamer_sharded in config check (#26958)
ahao-anyscale committed about 1 year ago
[CI] Enable Blackwell Llama4 MoE tests (#26731)
Michael Goin committed about 1 year ago
[ROCm][FEAT] Fuse DeepSeek shared experts into AITER fused_moe ops (#24097)
kliuae committed about 1 year ago
[Bugfix] reasoning_parser parameter handling in run_batch.py (#26225)
InChang Jeong committed about 1 year ago
[Qwen3-Next] Add tuned MoE config for Qwen3-Next FP8 on H100 tp2 (#26887)
felixzhu555 committed about 1 year ago
[ci] Adjusting AMD test composition 2025-10-14 (#26852)
Alexei-V-Ivanov-AMD committed about 1 year ago