[XPU] Delay BF16 check to worker init for spawn compatibility (#22979)

Chaojun Zhang committed about 1 year ago

[Bugfix][V1][P/D]Fix the issue where repeated requests for the same input produce abnormal outputs for P2pNcclConnector (#23403)

Zhonghua Deng committed about 1 year ago

[Kernel] Add fused grouped_topk kernel for MoE (#23274)

Xin Yang committed about 1 year ago

[test][RL] Add sleep level 2 test and fix reload with sleep mode (#23521)

22quinn committed about 1 year ago

[Refactor] Refactor persistent buffers with CpuGpuBuffer (#23515)

Woosuk Kwon committed about 1 year ago

[Bugfix] Fix Qwen3 MoE GPTQ inference (#23490)

Isotr0py committed about 1 year ago

Updates to Flex + VLLm integration (#21416)

Driss Guessous committed about 1 year ago

[Refactor] Pass `tokenizer` explicitly instead of binding to prompt update (#23542)

Cyrus Leung committed about 1 year ago

[Doc] Add caution for API server scale-out (#23550)

Cyrus Leung committed about 1 year ago

[Attention] Unify mamba and attention backend selection (#23171)

Ayush Satyam committed about 1 year ago

[misc] add shanghai meetup (#23535)

youkaichao committed about 1 year ago

[Bugfix] Allow dynamic number of patches for llava_onevision (#23525)

Cyrus Leung committed about 1 year ago

Feature/benchmark/random mm data/images (#23119)

Breno Baldas Skuk committed about 1 year ago

[Fix] DeepSeek V3.1 tool parser error message (#23492)

ZiTian Zhao committed about 1 year ago

[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711)

Chenguang Zheng committed about 1 year ago

[Refactor] Dynamic `target` and `content` for prompt updates (#23411)

Cyrus Leung committed about 1 year ago

[gpt-oss] use reasoning channel for reasoning text in serving_chat (#22920)

Yu Guo committed about 1 year ago

[Bugfix] Fix Dense module loading for sentence-transformers embedding models (simplified V2) (#23408)

LIYIFAN_liyifan committed about 1 year ago

Migrate DonutImagePixelInputs to TensorSchema (#23509)

Benji Beck committed about 1 year ago

Migrate skyworkr1v inputs to TensorSchema (#23499)

Benji Beck committed about 1 year ago