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
- [Bugfix] Fix AttributeError in pixtral/mistral3 graph mode (issue #43042)
- [Perf][Core] Use lazy deletion in PriorityRequestQueue
- fix: guard LLM response against empty choices (fixes #31501)
- Feat/fp8/fp4 persistent tma 3d kernels
- [Perf][Kernel] Fused QK-RMSNorm + mRoPE CUDA kernel for Qwen3-VL
- Support nvfp4 kv with kv-cache-dtype-skip-layers sliding_window
- [Bug]: vllm0.19.1 with llmcache with qwen3.6-27B-FP8 failed
- [Bug]: vllm-glm5.1 with llmcache with glm-5-fp8 failed
- [CPU] Support cpu compressed-tensor w8a8 int8 moe
- [Bugfix][KVConnector][NIXL] Sync engine_id across nodes for headless multi-node deployments
- Docs
- Python not yet supported