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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Route directly constructed embeddings through CPU offload
- [Bugfix][DSpark] Skip unregistered DeepSeek-V4 expert weights
- [XPU][CI] increase timeout of shutdown
- [Model][XPU] Enable fused QK-norm+RoPE+gate Triton kernel on XPU
- [Bugfix][XPU] Fall back to torch query when getMemoryInfo reports zero free memory
- [XPU][V2] Keep grammar-bitmask copies on the current stream under XPU graphs
- [XPU] Add gsm8k Eval for llama/qwen3-30b-a3b
- [Bug][Spec Decode] DSpark adaptive verification on SM90 (H20): draft acceptance collapse + hang during batch drain (sample_tokens RPC timeout)
- [Bug][CPU] GLM-5.x (glm_moe_dsa) cannot run on CPU: sparse attention forced by config, no way to disable
- [Perf][PCP] Fuse direct-KV publication fence
- Docs
- Python not yet supported