Bump actions/github-script from 8.0.0 to 9.0.0 (#39667)

dependabot[bot] committed 5 months ago

[MRV2] Also enable MRV2 for Llama and Mistral dense models (#43458)

Nick Hill committed 5 months ago

[Anthropic] Support system role messages inside messages array (#44283)

Chauncey committed 5 months ago

[Feature] Support EPLB for DeepSeek v4 Mega Moe (#43339)

Wei Zhao committed 5 months ago

[Bugfix] flashinfer: fail fast when --kv-cache-dtype nvfp4 used on unsupported arch (#43669)

Kartavya sonar committed 5 months ago

[BugFix] Fix Humming MoE deploy error (#43100)

Alireza Dadgarnia committed 5 months ago

[XPU] Enable rms_norm/act quant fusions (#43963)

liuzhenwei committed 5 months ago

[Refactor] Remove dead code from parser infrastructure (#44279)

Flora Feng committed 5 months ago

[Core] Move `max_concurrent_batches` to `VllmConfig` (#44274)

Nick Hill committed 5 months ago

[compressed-tensors] Asymmetric support for MoE WNA16 marlin (#44025)

Brian Dellabetta committed 5 months ago

[Misc] Support local image encoding in benchmarks (#43843)

XiaoZ committed 5 months ago

Migrate header files to torch stable abi (#44013)

Chris Leonard committed 5 months ago

[Rust Frontend] Cover different thinking modes in roundtrip tests (#44320)

Bugen Zhao committed 5 months ago

[ROCm] Fix AITER RMSNormQuantFusion for Kimi-Linear (#44308)

pschlan-amd committed 5 months ago

[Rust Frontend] Support recursive tool parameter conversion (#44299)

Bugen Zhao committed 5 months ago

[XPU] [Bug] remove xpuw4a16 output size check (#44168)

zofia committed 5 months ago

[BugFix] [GDN] Read linear_key_head_dim from hf_text_config for multimodal models (#43978)

IdoAtadTD committed 5 months ago

[FlashAttention] Sync FA with upstream (#44065)

Matthew Bonanni committed 5 months ago

[Bugfix] Vendor MiniCPMV/MiniCPMO processors to unblock Transformers v5 (#44282)

王金旭 committed 5 months ago

Support ModelOpt MXFP8 non-gated MoE (#42958)

TomerBN-Nvidia committed 5 months ago