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, 23:45 UTC
main
rasmith committed over 1 year ago
update flashinfer to v0.2.9rc2 (#21701)
weiliang committed over 1 year ago
Use `metavar` to list the choices for a CLI arg when custom values are also accepted (#21760)
Harry Mellor committed over 1 year ago
[P/D] Log warnings related to prefill KV expiry (#21753)
Nick Hill committed over 1 year ago
[Bugfix] Fix granite speech shape validation (#21762)
Cyrus Leung committed over 1 year ago
[XPU] IPEX-optimized Punica Wrapper on XPU (#21703)
Chaojun Zhang committed over 1 year ago
[CI/Build] Fix plugin tests (#21758)
Cyrus Leung committed over 1 year ago
[Bugfix] Mistral crashes on tool with no description (#21167)
Michard Hugo committed over 1 year ago
[Misc] Reduce logs for model resolution (#21765)
Cyrus Leung committed over 1 year ago
[Logs] Change flashinfer sampler logs to once (#21759)
Michael Goin committed over 1 year ago
[Bugfix][CI/Build] Update peft version in test requirement (#21729)
Isotr0py committed over 1 year ago
[Bugfix]check health for engine core process exiting unexpectedly (#21728)
wuhang committed over 1 year ago
[Docs] Add revision date to rendered docs (#21752)
Harry Mellor committed over 1 year ago
[Bugfix] Improve JSON extraction in LlamaToolParser (#19024)
Keyang Ru committed over 1 year ago
[`Ernie 4.5`] Name Change for Base 0.3B Model (#21735)
Anton Vlasjuk committed over 1 year ago
[PD] let p2p nccl toy proxy handle /chat/completions (#21734)
Chauncey committed over 1 year ago
[Bugfix] Fix glm4.1v video_grid_thw tensor shape scheme (#21744)
Isotr0py committed over 1 year ago
[Bugfix] Fix environment variable setting in CPU Dockerfile (#21730)
Li, Jiang committed over 1 year ago
[Bugfix] Fix Ernie4_5_MoeForCausalLM shared experts (#21717)
Jee Jee Li committed over 1 year ago
[feature] add log non default args in LLM (#21680)
rongfu.leng committed over 1 year ago