[Perf][ThinkingBudget] reduce search space for thinking tokens (#46425)

Walter Beller-Morales committed 4 months ago

[Test] Pin block_size in auto-fit max_model_len test (#45914)

Liangliang Ma committed 4 months ago

[Log] Update to log once (#46511)

Wentao Ye committed 4 months ago

[Bugfix] Re-enable FP8 MoE on NVIDIA Thor (#46339)

Cyrus Leung committed 4 months ago

[Doc] Document Qwen3.6 (dense + MoE) ViT CUDA graph support (#44720)

Nemani Harsha Vardhan committed 4 months ago

[ROCm] Fix AITER FP8 quantization schema tests (#46414)

djramic committed 4 months ago

[Model Runner V2][MM] Support EVS (#46535)

Nick Hill committed 4 months ago

[CPU][Perf] Accelerate unquantized MoE for AArch64 (#46353)

Fadi Arafeh committed 4 months ago

[Bugfix] Fix illegal memory access from a forward during a partial wake_up (#44483)

meihanc committed 4 months ago

[XPU] bump up vllm_xpu_kernels to v0.1.10.1 (#46607)

Kunshang Ji committed 4 months ago

[Perf][LoRA] Replace O(n) list.index() with a dict in convert_mapping (#46542)

Lynn committed 4 months ago

Fix duplicated logging when loading a corrupt or partial video (#46467)

Tae Jeong committed 4 months ago

[Misc][PD] Disable bidirectional xfer mode for NixlPushConnector (#46473)

Nicolò Lucchesi committed 4 months ago

Fix KV offload request-finished lifecycle contract (#46284)

Rui Yin committed 4 months ago

[XPU][Docker] switch to ubuntu 24.04 as base image (#45973)

Kunshang Ji committed 4 months ago

[Bugfix][Config] Keep pydantic validation for fields with a TYPE_CHECKING Literal alias (#46220)

Ting SUN committed 4 months ago

[Rust Frontend] Raise frontend JSON body limit (#46582)

Roy Wang committed 4 months ago

[KV Offload] Replace OffloadingHandler with OffloadingWorker (#45053)

Martin Hickey committed 4 months ago

[Feature] Triton INT4 per-token-head KV cache quantization (#40835)

JartX committed 4 months ago

[Mooncake] Only check and store new KV cache range (#46412)

Wei Zhao committed 4 months ago