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, 20:45 UTC
main
[ci][build] fix commit id (#6420)
youkaichao committed over 2 years ago
[Kernel] Turn off CUTLASS scaled_mm for Ada Lovelace (#6384)
Tyler Michael Smith committed over 2 years ago
Remove unnecessary trailing period in spec_decode.rst (#6405)
Yuan Tang committed over 2 years ago
[Model] Initialize Fuyu-8B support (#3924)
Isotr0py committed over 2 years ago
[ Misc ] Apply MoE Refactor to Deepseekv2 To Support Fp8 (#6417)
Robert Shaw committed over 2 years ago
[Misc] Add deprecation warning for beam search (#6402)
Woosuk Kwon committed over 2 years ago
[ Misc ] More Cleanup of Marlin (#6359)
Robert Shaw committed over 2 years ago
Updating LM Format Enforcer version to v10.3 (#6411)
Noam Gat committed over 2 years ago
[ci] try to add multi-node tests (#6280)
youkaichao committed over 2 years ago
[Docs] Clean up latest news (#6401)
Woosuk Kwon committed over 2 years ago
[Bugfix] Fix hard-coded value of x in context_attention_fwd (#6373)
Thomas Parnell committed over 2 years ago
Saliya Ekanayake committed over 2 years ago
[ci] Fix wording for GH bot (#6398)
Kevin H. Luu committed over 2 years ago
[Bugfix][TPU] Fix megacore setting for v5e-litepod (#6397)
Woosuk Kwon committed over 2 years ago
Fix release pipeline's dir permission (#6391)
Simon Mo committed over 2 years ago
[Misc] Add generated git commit hash as `vllm.__commit__` (#6386)
Michael Goin committed over 2 years ago
[Bugfix] Fix illegal memory access in FP8 MoE kernel (#6382)
Cody Yu committed over 2 years ago
Fix release pipeline's -e flag (#6390)
Simon Mo committed over 2 years ago
Fix interpolation in release pipeline (#6389)
Simon Mo committed over 2 years ago
Fix release-pipeline.yaml (#6388)
Simon Mo committed over 2 years ago