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 13, 04:30 UTC
main
[BugFix] Fix FA3 IMA with FULL_AND_PIECEWISE and cascade attention (default) (#28702)
Lucas Wilkinson committed 12 months ago
Fix KV sharing fast prefill with cudagraph enabled (#28537)
Yong Hoon Shin committed 12 months ago
[DCP] Support Decode Context Parallel (DCP) for GQA with Flashinfer (#25438)
Jingchun Gao committed 12 months ago
[Model][MM] Extract conv layer as CustomOp (#28455)
Shanshan Shen committed 12 months ago
[Frontend] Added chat-style multimodal support to /classify. (#27516)
Srreyansh Sethi committed 12 months ago
[Metrics] Log number of preempted requests (#28522)
lyn610 committed 12 months ago
[Misc] fix comment in test_envs (#28529)
Xing Liu committed 12 months ago
[Minor] avoid register new custom and just import silly_attn (#28578)
Boyuan Feng committed 12 months ago
Add output token counting to gsm8k eval (#28594)
Michael Goin committed 12 months ago
[BugFix] Fix multi-modal async scheduling race condition (#28706)
Nick Hill committed 12 months ago
[Bugfix] fix dots.ocr pp support (#28705)
Jiangyun Zhu committed 12 months ago
use default CCL_ZE_IPC_EXCHANGE (#28700)
Yan Ma committed 12 months ago
rasmith committed 12 months ago
rasmith committed 12 months ago
[Misc] add ignore mapper for quark quantization (#28275)
haoyangli-amd committed 12 months ago
[Misc] Update xformers to 0.33.0.post1 (#28678)
Roger Wang committed 12 months ago
[XPU][CI]disable lm cache uts (#28696)
Kunshang Ji committed 12 months ago
[Misc] Remove `warn_for_unimplemented_methods` (#28613)
Cyrus Leung committed 12 months ago
[ci][amd] fix basic models extra init test (#28676)
Bradley D committed 12 months ago
[CPU][Bugfix] Fix Apple Silicon M1 compilation failure (#28681)
Michael Goin committed 12 months ago