[EPLB] Change default EPLB communicator (#43110)

Ilya Markov committed 5 months ago

[LoRA] Reduce memory of 2D weights when EP is set (#42737)

Jee Jee Li committed 5 months ago

[BugFix] wire make_empty_intermediate_tensors on AyaVision and Voxtral (#43118)

Keyi Li committed 5 months ago

[Bugfix] Clear P0 mm sender cache on sleep/pause to fix mm_hash desync (#43001)

Tobias Wasner committed 5 months ago

[Misc] Replace assert with proper exceptions for security and validation in pooling (#43286)

Taneem Ibrahim committed 5 months ago

[XPU]feat: add XPU fallback for MoE topk routing and MXFP4 backend (#42951)

Ma Jian committed 5 months ago

[Attention] Mamba attention module refactor (#41126)

wangxiyuan committed 5 months ago

[CPU] Experimentally enable Triton and MRV2 (#43225)

Li, Jiang committed 5 months ago

[Docs] Note image preprocessing difference between qwen_vl_utils and vllm. (#43393)

wang.yuqi committed 5 months ago

Fix the docker build failure in tpu-inference (#43360)

mrjunwan-lang committed 5 months ago

[BugFix] Fix setuptools-rust dep in requirements files (#43377)

Nick Hill committed 5 months ago

Correcting the mock classes for MM GC tests (#43321)

Weida Hong committed 5 months ago

[CI] Fix "test_awq_load[gemma4-moe-*]" failure (#43296)

haosdent committed 5 months ago

[CI] Fix test_lora_with_spec_decode on V2 model runner (#43314)

haosdent committed 5 months ago

[Model] Fix MiniCPM-V 4.6 vit_merger qkv weight loading (#43213)

tc-mb committed 5 months ago

[Model] Use `AutoWeightsLoader` for Voyage (#42972)

Furkan F committed 5 months ago

[CI] De-flake renderers/test_hf.py::test_resolve_content_format_fallbacks[Qwen/Qwen-VL-string] (#43064)

haosdent committed 5 months ago

[XPU] Enable multiple key kernels for sparse attention (#37888)

Xiaochang Wu committed 5 months ago

[Bugfix] Make CuMemAllocator free callback stream-aware (#43020)

qizixi committed 5 months ago

[Frontend] DP Supervisor (#40841)

Wentao Ye committed 5 months ago