[Bugfix][LoRA] Add multimodal module mapping for Muse-Glimmer (#53513)

linitra24 committed 2 months ago

[LoRA] Add Qwen3-Omni multimodal LoRA support (#52786)

linitra24 committed 2 months ago

[Perf] Tune FlashInfer all-reduce selection on SM103 (#53318)

Summer Yang committed 2 months ago

[Bugfix][XPU] Skip oneCCL warm-up all_reduce when world_size == 1 (#52389)

DaeHyun Sung committed 2 months ago

[LoRA] feat: Support LoRA for DeepSeek V4 (#53361)

ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed 2 months ago

[Model] Add FP8 quantization support for ModernBERT (#53101)

ThunGuo committed 2 months ago

Reject oversized media before fully downloading it (#51896)

Clinton Thomas committed 2 months ago

feat: add SSE keep-alive comments for idle streaming responses (#51034)

Dieter Schwarzmann committed 2 months ago

Add MTP support for Nemotron VL models (#53121)

danisereb committed 2 months ago

[Misc] Use VLLMValidationError in Cohere request validation (#52467)

Frank committed 2 months ago

[Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460)

范裕达 committed 2 months ago

[RL] P2P RDT weight sync (#43375)

Aaron Hao committed 2 months ago

[Misc] Use VLLMValidationError in offline inference input validation (#53432)

Jensen Chen committed 2 months ago

Add routed expert loading for gpt-oss (#52209)

Wyett committed 2 months ago

[CI/Build] Pin Cython below 3.3 for arm64 tilelang sdist (#53358)

Kevin H. Luu committed 2 months ago

[MM] Simplify prompt updates: replace `PromptSeq` with `list[int]` (#53372)

Cyrus Leung committed 2 months ago

[Bugfix][Model] Mistral3: fix image placeholder grid for processor size overrides (#52874)

anmolgupt committed 2 months ago

[CI][AMD] Honor single-node Docker workload timeout (#52547)

Andreas Karatzas committed 2 months ago

[Rust Frontend][RL]: report engine world size over gRPC (#53204)

Biswa Panda committed 2 months ago

[ROCm][CI] Restore attention coverage after KV-cache layout refactor (#53351)

Andreas Karatzas committed 2 months ago