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 16, 05:45 UTC
main
[Doc][V1] Add V1 support column for multimodal models (#10998)
Roger Wang committed almost 2 years ago
[misc] clean up and unify logging (#10999)
youkaichao committed almost 2 years ago
[torch.compile][misc] fix comments (#10993)
youkaichao committed almost 2 years ago
[V1] Initial support of multimodal models for V1 re-arch (#10699)
Roger Wang committed almost 2 years ago
[torch.compile] allow candidate compile sizes (#10984)
youkaichao committed almost 2 years ago
[core][misc] remove use_dummy driver for _run_workers (#10920)
youkaichao committed almost 2 years ago
[core][executor] simplify instance id (#10976)
youkaichao committed almost 2 years ago
[BugFix][Kernel]: fix illegal memory access in causal_conv1d when conv_states is None (#10928)
zhou fan committed almost 2 years ago
[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975)
Cyrus Leung committed almost 2 years ago
[Model] Update multi-modal processor to support Mantis(LLaVA) model (#10711)
Cyrus Leung committed almost 2 years ago
[Doc] Explicitly state that InternVL 2.5 is supported (#10978)
Cyrus Leung committed almost 2 years ago
[Model] Composite weight loading for multimodal Qwen2 (#10944)
Cyrus Leung committed almost 2 years ago
[Misc][LoRA] Refactor and clean MergedQKVParallelLinearWithLora implementation (#10958)
Isotr0py committed almost 2 years ago
[Build] Fix for the Wswitch-bool clang warning (#10060)
Gregory Shtrasberg committed almost 2 years ago
[3/N] Support and implement merged input processor for LLaVA model (#10676)
Cyrus Leung committed almost 2 years ago
[Bugfix] Fix test-pipeline.yaml (#10973)
Jee Jee Li committed almost 2 years ago
[Core] Cleanup startup logging a bit (#10961)
Russell Bryant committed almost 2 years ago
[ci] fix broken tests (#10956)
youkaichao committed almost 2 years ago
youkaichao committed almost 2 years ago
[Doc] add KubeAI to serving integrations (#10837)
Sam Stoelinga committed almost 2 years ago