[XPU] Route weightless RMSNorm to _C dispatch (#47121)

Yintong Lu committed 3 months ago

[Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (#49291)

sungsoo ha committed 3 months ago

[Bugfix][Multimodal] Include media IO config in MM cache hash (#49975)

Guan-Ming Chiu committed 3 months ago

[KV Offload] Move CPUOffloadingSpec onto SharedOffloadRegion (#50094)

Chang Guo committed 3 months ago

[CI/Perf] Fix malformed serving benchmark config (#43538)

Minh Vu committed 3 months ago

[Rust Frontend] Add --limit-mm-per-prompt support (#49604)

Maria Guevara committed 3 months ago

[CI] Fix MXFP8 MOE backend selection tests on gfx942 (#50222)

fxmarty-amd committed 3 months ago

[EC Connector] Add has_pending_push_work (#49582)

omerpaz95 committed 3 months ago

[XPU] upgrade to torch 2.13 (#48677)

Yan Ma committed 3 months ago

[Misc][Minimax-M3]add default video_processor (#50092)

rongfu.leng committed 3 months ago

[BugFix] eagle draft max position embeddings (#49343)

Jared Wen committed 3 months ago

[Model] Support Qwen3.5 text-only dense and MoE models (#50210)

Perkz Zheng committed 3 months ago

[Model] Add Kimi K3 support: Python frontend [2/2] (#50093)

Bugen Zhao committed 3 months ago

[Frontend] Reuse prefill token ids on the decode chat path for disaggregated serving (#48145)

Seiji Eicher committed 3 months ago

[CPU] Fix FP8 attention scratchpad sizing (#50194)

Tianmu Li committed 3 months ago

[CI] Allow PR comment acknowledgements (#50211)

Kevin H. Luu committed 3 months ago

[XPU][UT][CI] add xpu config to run gpt-oss accuracy in ut and ci (#48703)

zofia committed 3 months ago

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

Jiangyun Zhu committed 3 months ago

fused_moe: add VLLM_TRITON_USE_TD tensor-descriptor path (#42436)

Artur Fierka committed 3 months ago

[Test] dynamic_shapes_compilation (#49974)

Jared Wen committed 3 months ago