[XPU][TEST] Add entrypoints test in Intel GPU CI (#53980)

xiangdong committed about 2 months ago

[Bugfix][Security] Bound embedding densification before to_dense() (#54632)

lzhan011 committed about 2 months ago

[Bugfix][Frontend] Preserve token offset origins after left text pre-trimming (#54692)

waizuichougou committed about 2 months ago

[CI][ROCm] Expand weight loading test coverage on AMD and cap its KV cache (#54037)

stefankoncarevic committed about 2 months ago

[Quantization][Refactor][1/N] Adopt `QuantKey` in `QuarkConfig` and methods, relying on `weight_quant_key`, `act_quant_key` for quant method dispatch (#52958)

fxmarty-amd committed about 2 months ago

[Distributed] Support pre-shared ncclUniqueId rendezvous for weight transfer (#53784)

dharak-cohere committed about 2 months ago

[Bugfix][Security] Bound the validation-error response body (#54684)

lzhan011 committed about 2 months ago

[Core] Release NCCL communicator memory in sleep mode (#51485)

aoshen02 committed about 2 months ago

[Feature][MM_UUIDs] Allow empty video URLs when using multi-modal UUIDs (#54220)

Jan Kwieciński committed about 2 months ago

[Bugfix][Frontend] Truncate the assistant tokens mask with the prompt (#54539)

Hotragn Pettugani committed about 2 months ago

[DecodeBenchConnector] Fix HMA cache-group mapping (#54647)

Jeff (Junze) Ma committed about 2 months ago

[ROCm][CI] Stabilize the sqrt-softplus top-k tie oracle (#54403)

Andreas Karatzas committed about 2 months ago

[Attention][DSA] Enable W4A16 DSA (#51724)

sychen52 committed about 2 months ago

[ROCm] Keep GLM-5.2 on MRV1 and disable default breakable cudagraph (#53155)

Rohan Potdar committed about 2 months ago

[ROCm][MoE] Split AITER CK and Triton MXFP4 W4A16 into separate backends (#50622)

afriedri committed about 2 months ago

[Distributed] Add opt-in FlashInfer PCIe IPC all-reduce backend (#53576)

Gabriel Wu committed about 2 months ago

[1/N][warmup][DSv4] Migrate generic MLA metadata and indexing kernels (#50175)

Roberto L. Castro committed about 2 months ago

[Bugfix][EC Connector] Fall back when MADV_POPULATE_WRITE is unsupported (#53190)

xiaolinchen committed about 2 months ago

[Feat] Add request-level preemption count histogram metric (#49984)

Amy (Yu-Hsuan) Lin committed about 2 months ago

[Kernel] add Flashinfer cutedsl w4a16 linear (#53014)

Lain committed about 2 months ago