[Rust Frontend] Bump llm-multimodal version (#47530)

Isotr0py committed 4 months ago

Move Roberta remaining nn.Embedding to VocabParallelEmbedding (#47452)

Max de Bayser committed 4 months ago

[Doc] Fix VLM2Vec benchmark chat template path (#47517)

Kalyanam Dewri committed 4 months ago

Add Triton Backend for Unlimited-OCR R-SWA (#47102)

Dakai An committed 4 months ago

[CI] Enable sccache for Rust build under CUDA/ROCm (#45246)

Bugen Zhao committed 4 months ago

[Rust Frontend] add repetition_detection support to sampling params (#46684)

yangyang-cs95 committed 4 months ago

New stable abi cleanup (#46656)

Chris Leonard committed 4 months ago

[XPU][CI]Fix dependency typo in Intel GPU CI (#47510)

xiangdong committed 4 months ago

[CPU][Build] Enable oneDNN ITT task collection by default for CPU primitive-level profiling (#47467)

Evgeny Parshutin committed 4 months ago

[XPU][CI]Mv huggingface cache to larger disk in Intel GPU CI (#47405)

xiangdong committed 4 months ago

[Rust Frontend] Recover buffered text from incomplete tool calls at EOS (#47289)

Reid committed 4 months ago

[Bugfix][Rust Frontend] Tolerate out-of-vocab prompt ids in detokenizer (#44682)

Ting SUN committed 4 months ago

[Bugfix][Gemma4] Keep image bidirectional attention within the sliding window (#47217)

Luciano Martins committed 4 months ago

[BugFix] Derive FlashInfer Q dtype from resolved per-group builder state (#47485)

Michael Goin committed 4 months ago

[CI] Pin modelscope version to fix test breakage (#47465)

Nick Hill committed 4 months ago

[ModelRunner V2][BugFix] Free all model refs on shutdown (#47483)

Nick Hill committed 4 months ago

[CI] intel CI: add quantization and awq case for xpu (#46456)

wenjun liu committed 4 months ago

Add Laguna XS.2.1 DFlash drafter support (#46853)

adamkbaranowski committed 4 months ago

[ROCm][CI] Adding extract hs 2gpu (#47482)

Andreas Karatzas committed 4 months ago

[ROCm][CI] Adding qwen3 dp4 eplb (#47480)

Andreas Karatzas committed 4 months ago