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 8, 01:15 UTC
main
[CI] Add GPT-OSS Eval job for H100 (#34359)
Michael Goin committed 9 months ago
[Model Runner V2] Minor CPU optimizations (#34856)
Nick Hill committed 9 months ago
[Bugfix] Fix benchmark_fused_collective crash on CustomOp init (#34665)
Mayank Ketkar committed 9 months ago
[UX] More descriptive reasons in is_supported_config for MoE (#34908)
Michael Goin committed 9 months ago
[Bugfix] Fix Basic Models Test (#34818)
Matthew Bonanni committed 9 months ago
[Bugfix] Fix cutlass fp8 kernel on hopper for Qwen3.5 (#34914)
Roger Wang committed 9 months ago
Change targets for AMD build in the "CI" pipeline (#34918)
Alexei-V-Ivanov-AMD committed 9 months ago
[Refactor] Deprecate `head_first` for `chunk_gated_delta_rule` (#34263)
Wentao Ye committed 9 months ago
Revert "[NemotronH] Do not force router to run in fp32 (#34582)" (#34808)
roikoren755 committed 9 months ago
[Model Bash][DeepSeekR1] Remove Shared Expert Clone (#34344)
Robert Shaw committed 9 months ago
Eldar Kurtić committed 9 months ago
[Bugfix] Qwen3.5 kv-scale weight remapping (#34719)
Linda committed 9 months ago
[CI/Build] Try to make beam search test less flaky (#34885)
Cyrus Leung committed 9 months ago
[Bugfix] Fix edge case in UUID data parsing (#34884)
Cyrus Leung committed 9 months ago
Andreas Karatzas committed 9 months ago
[ROCm][CI] Removing all blocking labels from MI355 until stable infra (#34879)
Andreas Karatzas committed 9 months ago
[Voxtral Realtime] Fix engine crash on empty multimodal embeddings (#34862)
Tal Nir committed 9 months ago
[Bug] Fix DeepSeek V3 weight loading caused by incorrect prefix (#34876)
Wei Zhao committed 9 months ago
[Bugfix] Add Quant Config to Llava Next Projector (#34847)
Alex Brooks committed 9 months ago
fix(docs): fix typos in comments and docstrings (#34836)
Manrique Vargas committed 9 months ago