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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI] Mooncake PD integration tests
- [MRV2][Spec] Fuse AR speculator multi-step decodes back into one CUDA graph
- [Kernel] Manual activation+quant fusion via QuantizedActivation
- Remove redundant `_pack_topk_ids_weights_kernel` in TrtLLM NvFP4 MoE
- Revert "[Bugfix][Model] Support tensor parallelism for DiffusionGemma (#45719)" (#46177)
- [WideEP] Add NCCL EP all2all backend for expert parallelism
- [Bugfix] Parse JSON tool calls in Llama 4 pythonic parser
- [CI/Test] Skip FlashAttnMLA + FP8 KV cache cell in test_mla_rope_kvcache_cat_fusion
- [Hybird][PrefixCache] Pre-copy-free align prefix cache
- [Bug][Metrics] `get_metrics_snapshot()` raises on unknown metric types, crashing LLM.get_metrics() and the ORCA header path
- Docs
- Python not yet supported