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 4, 00:00 UTC
main
[SpecDecoding] extend mtp support for mimo 2.5 (#41905)
Jiangyun Zhu committed 6 months ago
[Model] use AutoWeightsLoader for DeepSeekV2 (#41706)
SoluMilken committed 6 months ago
[BugFix] Fix Gemma4 'layers.0.moe.experts.0.down_proj_packed' KeyError issue (#40708)
SoluMilken committed 6 months ago
[Bugfix][PD] Fix DSv4 Disaggregated (#41957)
Nicolò Lucchesi committed 6 months ago
Thomas Parnell committed 6 months ago
Kermit committed 6 months ago
[DSv4] Improved fused Indexer Q quant kernel (#41428)
Thien Tran committed 6 months ago
[ROCm] Upgrade aiter to v0.1.13-rc5 (#42113)
Micah Williamson committed 6 months ago
[LoRA] Initial EP support for LoRA (#40867)
Jee Jee Li committed 6 months ago
Require C++20 for compatibility with PyTorch (#40380)
Richard Barnes committed 6 months ago
[Bugfix] Preserve leading/trailing whitespace in GLM non-streaming tool parser (#42026)
Rishapveer Singh committed 6 months ago
[Models] Cohere Eagle + fix to Cohere MoE (#42078)
Terrence Zhao committed 6 months ago
[ROCm][Bugfix] Re-tag AITER MoE weights as preshuffled after replace_parameter (#42061)
Markus Hartikainen committed 6 months ago
David Zheng committed 6 months ago
Add @Harry-Chen in CODEOWNERS (#42130)
Shengqi Chen committed 6 months ago
[CI][Bugfix] Make test_gpt2_cache_hit observable across V1 EngineCore (#42037)
haosdent committed 6 months ago
[Bugfix] Fix test_whisper distributed test process handling (#42038)
David Zheng committed 6 months ago
[XPU] update supported models on XPU (#41911)
Yan Ma committed 6 months ago
[Docs] Update server entrypoint examples (#42077)
Ethan Feng committed 6 months ago
[Docs] Fix RLHF example links (#42073)
Ethan Feng committed 6 months ago