[XPU][UT] skip GLM-5.3-Flash test on XPU (#55266)

Qiming Zhang committed about 2 months ago

[Docs] Add example for Renderer.render_cmpl() usage (#54265)

Shaurya Pratap Srivastava committed about 2 months ago

[Rust Frontend] Record Mooncake/NIXL KV-connector metrics (#52755)

Ilya Markov committed about 2 months ago

[Bugfix] Reject tokenizer-less Qwen VL processor init (#54886)

Luyi Xiao committed about 2 months ago

docs: note that enforce_eager also disables torch.compile (#55271)

Anshul Desai committed about 2 months ago

[Bugfix][Docs] Package glm5next nvidia subtree and fix its docstrings (#55214)

Harry Mellor committed about 2 months ago

[Bugfix][KV Connector] Fix DecodeBenchConnector prefix block selection (#54878)

Jeff (Junze) Ma committed about 2 months ago

[ROCm][CI] Bump ROCk base to ROCm 10.0 (#55246)

Rohan Potdar committed about 2 months ago

[EC Connector] P2P NIXL + CPU EC Connector (#47941)

omerpaz95 committed about 2 months ago

[Performance][DSv4] Size dequant gather launch grid by rows (#55061)

aoshen02 committed about 2 months ago

[Bugfix][PD] Pad resumed speculative decode requests (#55126)

Ziming Huang committed about 2 months ago

[KVConnector] Add retention interval to OffloadingConnector (#51886)

bnellnm committed about 2 months ago

[ROCm][CI] Build and publish TheRock nightly docker images (#55014)

Rohan Potdar committed about 2 months ago

[Core][KV Events] Echo session_id on GPU BlockStored events (#51381)

guangli_Liu committed about 2 months ago

[Bugfix][DCP] Materialize prefill keys on non-owner ranks (#54908)

Yunxiao Ning committed about 2 months ago

[Perf][Model Runner V2] Compact sampling masks on GPU instead of unpacking the full-vocab bitmask on CPU (#54901)

aoshen02 committed about 2 months ago

[Rust Frontend] Report reasoning tokens in chat completion usage (#54883)

Bugen Zhao committed about 2 months ago

[ROCm] Bump AITER to 0.1.21.post1 (#52826)

Rohan Potdar committed about 2 months ago

[Perf] Prefetch the weight before the PDL wait in fused_q_kv_rmsnorm (#55020)

Yongye Zhu committed about 2 months ago

[Perf][Kimi-K3] Cut MLA decode concat/cache epilogue latency (#54896)

Yongye Zhu committed about 2 months ago