A high-throughput and memory-efficient inference and serving engine for LLMs
main
[Rust Frontend] Enable Qwen4-exp multimodal support (#54813)
Isotr0py committed about 2 months ago
[Bugfix][KV Connector] Fix Mooncake physical-block transfer length (#54272)
Zhewen Li committed about 2 months ago
[Bugfix][Mooncake] Offload producer partial tails on request finish (#52832)
Dao007forever committed about 2 months ago
[Bugfix][Profiler] Fix API server crash on double /stop_profile (#51678)
Alberto Massidda committed about 2 months ago
[ROCm][MoE] Fix gfx950 block scale swizzle for AITER Triton MXFP4 W4A16 (#54773)
stefankoncarevic committed about 2 months ago
[Rust Frontend] Bound recursive argument parsers (#54303)
Bugen Zhao committed about 2 months ago
[Chore] Remove redundant `_pack_topk_ids_weights_kernel` in TrtLLM NvFP4 MoE (#46872)
Julien Debache committed about 2 months ago
[Bugfix] Log platform plugin detection failures (#52285)
Luyi Xiao committed about 2 months ago
[ROCm][CI] Add ROCm misc ops and env tests (#53279)
Divakar Verma committed about 2 months ago
[Feature] Avoid flashinfer autotune each time when vllm source change (#54794)
Wentao Ye committed about 2 months ago
[Bugfix][Frontend] Honor skip_decoder_start_token in async encoder-decoder rendering (#54799)
waizuichougou committed about 2 months ago
[Bugfix][Frontend] Restore the chat template content format mismatch warning (#54622)
Pratham Shirbhate committed about 2 months ago
[CI] Speed up quantization test group (#53291)
fxmarty-amd committed about 2 months ago
[Bugfix] Drop incomplete tool-call markup in non-streaming to match streaming (#47562)
Suvrakamal Das committed about 2 months ago
[Misc] Share Buildkite CI failure skill across agents (#54806)
Misha Goin committed about 2 months ago
[KV Connector] Support heterogeneous TP sharing in Mooncake Store Connector (#53129)
周峥 committed about 2 months ago
[Fix] Fix FSE compatibility detection for Quark-produced models (#54573)
fxmarty-amd committed about 2 months ago
[Perf][Kernel] Initialize NVFP4 padding in quant kernel (#53568)
Roberto L. Castro committed about 2 months ago
[Bugfix] Support Sentence Transformers 5.4+ serialized configs (#54533)
Eli Nabro Yeongmin Oh committed about 2 months ago
[Transformers backend] Replace vocab embeddings in `recursive_replace` (#54760)
Harry Mellor committed about 2 months ago