[Model] DeepSeek-V4.1-Flash Model Definitions (#56228)

Roger Wang committed about 1 month ago

[Doc] Sync KV event medium terminology after #48123 (#51646)

AlexHuang committed about 1 month ago

[NIXL][PCP] Report replicated-PCP ranks > 0 as done sending instead of hiding them (#53903)

Lucas Wilkinson committed about 1 month ago

[Docs][Security] Clarify reporter credit and CVE publication timing (#55476)

Juan Pérez de Algaba committed about 1 month ago

[Kimi K3 Perf] Avoid KDA mixed-batch gather/scatter, 5.2%~7.7% E2E Throughput Improvement (#56159)

Wentao Ye committed about 1 month ago

[XPU][Bugfix] Add forward_xpu to Ernie4_5_VLRotaryEmbedding (#55942)

Jakub Byczkowski committed about 1 month ago

[XPU][Bugfix] Fix FalconH1 pipeline-parallel execution (#55913)

Jakub Byczkowski committed about 1 month ago

[Model] Add Bailing V3 VL support (#55921)

zexplorerhj committed about 1 month ago

[ROCm] Add better kv dtype error discoverability (#55236)

Giuseppe Grossi committed about 1 month ago

[BugFix] Retain both replay boundaries so an EAGLE resend of a block-aligned prompt still hits (#54713)

Toby Mao committed about 1 month ago

[Perf][GLM-5.3-Flash] Decode hot-path cleanups: strided KDA recurrent inputs, NoPE MQA query without concat, no duplicate router GEMM (#55736)

Jared Wen committed about 1 month ago

[Model][Frontend] Support DeepSeek-V4.1-Flash in Rust and Python frontends (#56208)

Bugen Zhao committed about 1 month ago

[ROCm][Perf] Kimi-K3 Fused kernels for KDA prefill reland (#54038)

kliuae committed about 1 month ago

[Kernel] Optional Q-norm in fused DSv4 MLA epilogue; group_size=32 for packed FP8 quant (#56215)

Yongye Zhu committed about 1 month ago

[Bugfix] Tolerate misspelled DSML tool_calls wrapper (#56141)

Flora Feng committed about 1 month ago

[Bugfix][MRV2] Initialize DCP metadata after batch partitioning (#55212)

Sy03 committed about 1 month ago

[multimodal][feat] add torchaudio backend to AudioResampler (#52598)

Jared Wen committed about 1 month ago

[ROCm][Perf] Route large DSV4 sparse prefill to AITER OPUS (#54855)

jiacao-amd committed about 1 month ago

[MM][CG] Enable encoder CUDA Graph for MiniCPM-V (#42785)

Yunzhu Lu committed about 1 month ago

[Model] Add DeepSeek-V4 CPU backend (#55355)

Li, Jiang committed about 1 month ago