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 12, 14:45 UTC
main
[NIXL] Use config to enable telemetry + NIXL version bump (#29305)
Nicolò Lucchesi committed 12 months ago
[Build/CI][DP/EP] Add QWen/Qwen3-30B-A3B-FP8 + EPLB tests to Nightly H100 and B200 (#29195)
Varun Sundar Rabindranath committed 12 months ago
[Bugfix] properly handle nested json with llama3 tool parser (#27701)
Aydin Abiar committed 12 months ago
[Bugfix] [ROCm] [UX] Reorganize ROCm Backend Selection Logic (#26980)
vllmellm committed 12 months ago
Add option to use unbacked, and backed size obl dynamic shapes for more sounds compilation. (#26199)
Laith Sakka committed 12 months ago
Update KServe guide link in documentation (#29258)
Yuan Tang committed 12 months ago
[EPLB] Optimize EPLB for Async Rearrange Experts (#22179)
WeiQing Chen committed 12 months ago
[CPU][IBM Z] Fix BF16 support and vectorize math operations for s390x (#28926)
R3hankhan committed 12 months ago
[Doc]: fix typos in various files (#29230)
Didier Durand committed 12 months ago
[Bugfix][Rocm] Fix shared expert weight loading failure in DeepSeek-MTP (#27563)
杰兮 committed 12 months ago
[Feature][Benchmark] add --link-vars can filter when serve_param equal bench_param (#28909)
rongfu.leng committed 12 months ago
[BugFix] Fix R-VL model loading error (#29299)
Fanli Lin committed 12 months ago
[Core] Deprecate `xformers` (#29262)
Roger Wang committed 12 months ago
[ROCm] Support for Whisper v1 with Aiter Unified Attention and Aiter Flash Attention (#28376)
tongqiu committed 12 months ago
[Model] Add OpenCUA-7B support (#29068)
Zero committed 12 months ago
[LoRA] Optimize 3D MoE logic (#29222)
Jee Jee Li committed 12 months ago
Josh Moore committed 12 months ago
[Model Runner V2] Add apply_temperature option to gumbel_sample (#29276)
Woosuk Kwon committed 12 months ago
[Model Runner V2] Optimize CUDA graph capture time (#29275)
Woosuk Kwon committed 12 months ago
[Model Runner V2] Support spec decoding [1/N] (#29274)
Woosuk Kwon committed 12 months ago