vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug] CUTLASS MoE backend unavailable on SM_120/SM_121 (consumer Blackwell / DGX Spark) for tensor/token-scaled FP8 models
- [Feature]: Porting `QKNormRoPEFusionPass` to manual fusion
- [Feature]: Porting `RMSNormQuantFusionPass` to manual fusion
- [Feature]: Porting `AttnQuantFusionPass` to manual fusion
- [Feature]: Porting `MLARoPEKVCacheCatFusionPass` to manual fusion
- [Bug]: Hybrid Mamba + KV connector disagg blocked by _mamba_block_aligned_split assertion (NemotronH-550B repro)
- [Bugfix] Respect CompilationMode.NONE / eager backend in VocabParallelEmbedding.get_masked_input_and_mask
- [Docs] Update deprecated VLLM_FLASHINFER_MOE_BACKEND reference
- [Examples] Fix use_beam_search type in dummy_client.py
- [Perf] Add tuned MoE configs for E=256, N=512/1024 on H100/H200/B200
- Docs
- Python not yet supported