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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] RayExecutorV2: Defer `vllm_config` deserialization until after `CUDA_VISIBLE_DEVICES` is set
- [Feature][Frontend] Add prefix cache hit rate to usage details
- Fix sparse BlockStored event token/hash mapping
- [Bugfix][Spec-Decode][MLA] Fix CUDA graph capture assertion and missing draft seq_lens_cpu_upper_bound for EAGLE on SINGLE_ONLY MLA backends
- [Bugfix] Fix ZMQ port TOCTOU race in shm_broadcast.py
- [WIP][Kernel][CuTeDSL] Quant Scaled MM Per (Tensor/token/channel) FP8/INT8 kernel in CuTeDSL
- fix: logprobs values change with requested count due to token-string collision
- [Feature][Spec-Decode]: Cascade: Utility-Driven Adaptive k for MoE Speculative Decoding in V1
- [Frontend] Consolidate scale out entrypoints
- [XPU] Add online fp8 quantization test
- Docs
- Python not yet supported