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 6, 13:15 UTC
main
[Bugfix] Fix DP MTP Dummy Run (#35243)
Benjamin Chislett committed 8 months ago
[openapi] remove redundant exception stack trace[4/N] (#37157)
Ning Xie committed 8 months ago
[`UltraVox`] Fix output type (#37224)
Anton Vlasjuk committed 8 months ago
[Chore] Replace all base64 usages with faster pybase64 package (#37290)
Isotr0py committed 8 months ago
[Misc][LoRA] Add --lora-target-modules to restrict LoRA to specific modules (#34984)
Bhoomit committed 8 months ago
Fix Phi3 test that fails with Transformers v5 (#37298)
Harry Mellor committed 8 months ago
[Bugfix] Fix unclean shutdown crash with AllReduce Fusion workspace (#36955)
Siew's Capital Jarvis committed 8 months ago
pick up tuned prefill configs for FP8 FA3 (#36265)
Jonas M. Kübler committed 8 months ago
[Frontend] Complete OpenAI render delegation (#37287)
Sage committed 8 months ago
[Misc] Use VLLMValidationError in batch, pooling, and tokenize protocol validators (#36256)
Umut Polat committed 8 months ago
[1/2] Move InternVL-based processors (#37260)
Cyrus Leung committed 8 months ago
Bugfix for offloading+prefetch for GLM-4.7-FP8 (#37178)
sfbemerk committed 8 months ago
Add gigachat 3.1 tool parser + fix gigachat3 tool parser (#36664)
Viacheslav committed 8 months ago
[perf][connector] optimize build_connector_meta when host buffer transfer is not used (#37165)
youkaichao committed 8 months ago
[Frontend] Delegate tokenization serving preprocessing to OpenAIServingRender (#37266)
Sage committed 8 months ago
[Bugfix](xpu): prevent “selected index k out of range” in TP decode path (#37259)
zhao, zhenhui committed 8 months ago
[Feature]: Support for multiple embedding types in a single inference call (#35829)
Augusto Yao committed 8 months ago
[Bugfix][ResponsesAPI] Fix crash when tool_choice=required exceeds max_output_tokens (#37258)
Chauncey committed 8 months ago
Fix infinite recursive search issue in quark.py (#32779)
xiao-llm committed 8 months ago
[Bugfix] Fix NemotronH MTP + Chunked Prefill (#35447)
Benjamin Chislett committed 8 months ago