[CI] [Bugfix] Fix unbounded variable in `run-multi-node-test.sh` (#31967)

TJian committed 10 months ago

[OpenAI] Fix tool_choice=required streaming when output has trailing extra data (#31610)

Mary committed 10 months ago

[Model] Enable LoRA support for Pixtral (#31724)

Ce Zhao committed 10 months ago

[Model] Add LFM2-VL model support (#31758)

tianshu-Michael-yu committed 10 months ago

[Model] Add Grok-2 (#31847)

Bijaya Dangol committed 10 months ago

[Voxtral] Fix speech transcription api (#31388)

Patrick von Platen committed 10 months ago

[MM Encoder]: Make MMEncoderAttention's `scale` takes effect properly (#31950)

Isotr0py committed 10 months ago

[Model] Standardize common vision encoders (#31947)

Cyrus Leung committed 10 months ago

[Chore] Further cleanup pooler (#31951)

Cyrus Leung committed 10 months ago

RayLLM Bugfix - Preserve obj store URL for multi engine_config creation (#30803)

omer-dayan committed 10 months ago

[Misc] Support qwen3-next lora (#31719)

BingjiaWang committed 10 months ago

fix(compile): apply partition wrapper when loading AOT cached functions (#31536)

DevByteAI committed 10 months ago

[CI/Build] Enable test_kv_cache_events_dp for AMD (#31834)

Ryan Rock committed 10 months ago

Decouple page_size_bytes calculation in AttentionSpec for TPU/RPA Compatibility. (#31635)

Lumosis committed 10 months ago

[Models] Allow converting Qwen3-VL into Reranker model (#31890)

Isotr0py committed 10 months ago

[ROCm]Skip test_torchao.py::test_pre_quantized_model on CDNA3 arch (#31905)

Zhiwei committed 10 months ago

[docker] A follow-up patch to fix #30913: `[docker] install cuda13 version of lmcache and nixl` (#31775)

Shang Wang committed 10 months ago

fix(rocm): Add get_supported_kernel_block_sizes() to ROCM_ATTN (#31712)

Rabi Mishra committed 10 months ago

[Model] Enable LoRA support for tower and connector in GLM4-V (#31652)

Zyyeric committed 10 months ago

[Bugfix] Remove the num_hidden_layers override for glm4_moe (#31745)

Andy Liu committed 10 months ago