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 10, 01:30 UTC
main
[Docs][Governance] Add @robertshaw2-redhat to lead maintainers group (#32498)
Simon Mo committed 10 months ago
[TPU][Core] Enable Pipeline Parallelism on TPU backend (#28506)
Chenyaaang committed 10 months ago
[CI] Fix OOM in Hopper Fusion E2E Tests (H100) (#32489)
Lucas Wilkinson committed 10 months ago
[responsesAPI] allow tuning include_stop_str_in_output (#32383)
Andrew Xia committed 10 months ago
[LoRA] Update LoRA expand kernel heuristic (#32425)
Xin Yang committed 10 months ago
Atomics Reduce Counting Optimization for SplitK Skinny GEMMs. (#29843)
Hashem Hashemi committed 10 months ago
[CI] Update deepgemm to newer version (#32479)
Wentao Ye committed 10 months ago
[EPLB][BugFix]Possible deadlock fix (#32418)
Ilya Markov committed 10 months ago
[CI][AMD] Skip test_permute_cols since the kernel is not used and not built for ROCm (#32444)
rasmith committed 10 months ago
[Chore] Replace swish with silu (#32459)
Cyrus Leung committed 10 months ago
[ROCm][CI] Skip Qwen3-30B-A3B-MXFP4A16 Eval Test On Non-CUDA Platforms (#32460)
Micah Williamson committed 10 months ago
fix(rocm): Enable non-gated MoE (is_act_and_mul=False) support on ROCm (#32244)
Rabi Mishra committed 10 months ago
[Bugfix] Refactor to support DP parallel in R3 (#32306)
Hongxin Xu committed 10 months ago
[CI] Breakup h200 tests (#30499)
Lucas Wilkinson committed 10 months ago
[Frontend][1/n] Make pooling entrypoints request schema consensus | CompletionRequest (#32395)
wang.yuqi committed 10 months ago
[Bug] Add TPU backend option (#32438)
XiongfeiWei committed 10 months ago
[bugfix] Fix online serving crash when text type response_format is received (#26822)
cjackal committed 10 months ago
[Bugfix] [DeepSeek-V3.2] fix sparse_attn_indexer padding (#32175)
Kebe committed 10 months ago
[Model] Add Step3vl 10b (#32329)
ltd0924 committed 10 months ago
[ROCm][CI] Enable AITER Unified Attention On ROCm For gpt-oss Test (#32431)
Micah Williamson committed 10 months ago