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 15, 07:15 UTC
main
[Docs] Add developer doc about CI failures (#18782)
Russell Bryant committed over 1 year ago
[Misc] Fix path and python alias errors in disagg_prefill exmaples (#18919)
Jiaxin Shan committed over 1 year ago
feat: add data parallel rank to KVEventBatch (#18925)
Yan Ru Pei committed over 1 year ago
Chen Zhang committed over 1 year ago
[Bugfix][P/D] Fix Prefix Cache Bug (#18411)
Nicolò Lucchesi committed over 1 year ago
Chauncey committed over 1 year ago
[Bugfix] get_num_blocks_to_allocate with null_block (#19031)
Chen Zhang committed over 1 year ago
[V1][Spec Decode][Ngram] 1.35x gain -> 1.95x gain on InstructCoder with prompt fix (#18971)
Ekagra Ranjan committed over 1 year ago
[v1] Re-init input batch for multiple kv cache groups (#18654)
Chen Zhang committed over 1 year ago
Fix interaction between `Optional` and `Annotated` in CLI typing (#19093)
Harry Mellor committed over 1 year ago
[Perf] Tune `scaled_fp8_quant` by increasing vectorization (#18844)
Michael Goin committed over 1 year ago
[V1] Support cross-layer KV sharing (#18212)
Yong Hoon Shin committed over 1 year ago
[Kernel] DeepEP dispatch-combine kernel integration (#18434)
Varun Sundar Rabindranath committed over 1 year ago
[doc] update docker version (#19074)
Reid committed over 1 year ago
[Doc] Readme standardization (#18695)
SorenDreano committed over 1 year ago
[Misc] Add SPDX-FileCopyrightText (#19100)
Simon Mo committed over 1 year ago
[Misc] fix: add miss best_of param validation (#18555)
CYJiang committed over 1 year ago
[Misc] Add missing `_Backend` enums (#19081)
Nicolò Lucchesi committed over 1 year ago
[Doc] Improve the Pull Request template with key components (#19086)
Lu Fang committed over 1 year ago
[Bugfix] disable processor cache (#19068)
Raushan Turganbay committed over 1 year ago