A high-throughput and memory-efficient inference and serving engine for LLMs
main
[Hardware][AMD][CI] Fix Kernels Quantization test timeout (#46859)
Matt committed 4 months ago
[Bugfix][Model] Support tensor parallelism for DiffusionGemma (#45719) (#46177)
Carlos Alvarado Martinez committed 4 months ago
[Bugfix][Parser] Pass token IDs to parser.parse() in Responses API and batch serving (#46843)
Ben Browning committed 4 months ago
[CPU] Fix macOS/Apple Silicon hang by enabling OpenMP in the build (#46769)
Michael Goin committed 4 months ago
Migrate Voxtral to mistral-common 1.11.5 audio API (#46705)
Julien Denize committed 4 months ago
[ModelRunner V2] Update scheduler tests to cover MRV2 paths (#46771)
Nick Hill committed 4 months ago
[CI/Build][CPU] Add test image cache clean-up (#46831)
Li, Jiang committed 4 months ago
[Core] Add `VLLM_GPU_SYNC_CHECK` env var (#44800)
Nick Hill committed 4 months ago
[Rust Frontend] Use `oss-harmony` for Harmony output processing (#46799)
Bugen Zhao committed 4 months ago
[CI] Fix failing CUDA graph capture in Triton MOE (#46735)
fxmarty-amd committed 4 months ago
Hongxia Yang committed 4 months ago
[ROCm] [Performance] Optimize aiter moe for DeepSeekV4 (#46122)
TJian committed 4 months ago
[ROCm]Enable AITER MoE backend for MiniMax-M3-MXFP4 (#46419)
qli88 committed 4 months ago
TJian committed 4 months ago
[API] Add token offsets to render endpoints (/v1/.../render) (#44226)
Hyunkyun Moon committed 4 months ago
[ROCm] Fix AITER_UNIFIED_ATTN Dispatching After AITER Bump (#46780)
Micah Williamson committed 4 months ago
[Docs] Remove BambaForCausalLM from supported hybrid models list (#46071)
AgenticSpark committed 4 months ago
[Misc] Move the legacy api_server.py to the examples directory. (#46783)
wang.yuqi committed 4 months ago
[Bugfix][Tool Parser] PoolsideV1: fix string whitespace and required named tool choice (#46486)
Joe Rowell committed 4 months ago
Remove grok model arch from vllm (#46706)
Tiezhen WANG committed 4 months ago