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
[Model] MTP fallback to eager for DeepSeek v32 (#25982)
Lucia Fang committed about 1 year ago
[Misc] Make EP kernels install script support uv (#25785)
Lucas Wilkinson committed about 1 year ago
[gpt-oss] use vLLM instead of openai types for streaming (#25186)
Andrew Xia committed about 1 year ago
[Docs] Remove API Reference from search index (#25949)
Harry Mellor committed about 1 year ago
Add explicit pooling classes for the Transformers backend (#25322)
Harry Mellor committed about 1 year ago
[V1] [P/D] Add Support for KV Load Failure Recovery (#19330)
David Ben-David committed about 1 year ago
[Bench] Add DeepSeekV32 to MoE benchmark (#25962)
Jee Jee Li committed about 1 year ago
cjackal committed about 1 year ago
OffloadingConnector: Fix GPU block tracking bug (#25856)
Or Ozeri committed about 1 year ago
[Docs] Add moe kernel features doc (#25297)
bnellnm committed about 1 year ago
[Doc] Improve MM Pooling model documentation (#25966)
Cyrus Leung committed about 1 year ago
[Bug] Fix AttributeError: 'QKVParallelLinear' object has no attribute 'orig_dtype' (#25958)
Wentao Ye committed about 1 year ago
[bugfix][deepseek] fix flashmla kernel selection (#25956)
youkaichao committed about 1 year ago
[Bugfix] Token type and position embeddings fail to be applied to `inputs_embeds` (#25922)
Cyrus Leung committed about 1 year ago
[Bugfix] Fix accuracy issue of TRTLLM FP8 MOE and improve logging (#25895)
Pavani Majety committed about 1 year ago
[Bugfix][Model] Fix inference for Hunyuan dense models (#25354)
Anion committed about 1 year ago
Add Hugging Face Inference Endpoints guide to Deployment docs (#25886)
Sergio Paniego Blanco committed about 1 year ago
[Kernel][Moe Configs] Add more tuned triton configs for ExpertsInt8 and FP8 (#25858)
Asaf Joseph Gardin committed about 1 year ago
[Fix] Improve CPU backend compatibility for RISC-V (#25816)
ihb2032 committed about 1 year ago
[CI] Move applicable tests to CPU (#24080)
Reza Barazesh committed about 1 year ago