A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 11, 23:45 UTC
main
[BugFix] Fix DBO assert `assert B_block_table == B_q` (#29933)
Lucas Wilkinson committed 11 months ago
Peng-YM committed 11 months ago
Mercykid-bash committed 11 months ago
Access `partial_rotary_factor` from `rope_parameters` (#29966)
Harry Mellor committed 11 months ago
Kuntai Du committed 11 months ago
[Bugfix] Fix FP8 MoE LoRA (#29890)
Jee Jee Li committed 11 months ago
support qwen3-vl handle requests with embeddings (#30037)
Tao Yun committed 11 months ago
[CI][DCP][Perf] reduce DCP CI execution time (#29858)
Qiu committed 11 months ago
[Chore] Deprecate `merge_by_field_config` arg (#30035)
Cyrus Leung committed 11 months ago
[Doc] clarify nightly builds in developer docs (#30019)
Shengqi Chen committed 11 months ago
Mark DBO test as flaky on b200 for Distributed B200 test (#29913)
Doug Smith committed 11 months ago
[Model Runner V2] Implement get_num_sampled_and_rejected kernel (#30029)
Woosuk Kwon committed 11 months ago
Use Transformers v5 RoPE standardisation and validation (#30046)
Harry Mellor committed 11 months ago
Fix broken multiline assert in `LoRAModelManager.register_module` (#30032)
Yongtao Huang committed 11 months ago
Delete HF version of Phi 4 MM (#30049)
Harry Mellor committed 11 months ago
[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)
wang.yuqi committed 11 months ago
[release] install regex (#30008)
Kevin H. Luu committed 11 months ago
[Bugfix] Fix the issue with interleaved thinking when using streaming (#30033)
Chauncey committed 11 months ago
[ROCm][CI][Bugfix] Fixing the `Multi-Modal Models Test (Extended) 1` group (#30013)
Andreas Karatzas committed 11 months ago
Validating Runai Model Streamer Integration with S3 Object Storage (#29320)
Noa Neria committed 11 months ago