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 supported48 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Add SM120 (RTX 6000/5000 Blackwell) support for native NVFP4 MoE kernels
- [Bug]: ModelOpt Llama-4 Checkpoints Take 5+ minutes to load
- [Bugfix] Add warning when model generates immediate EOS token
- [Feature] Add `qwen2_5_coder` tool parser for Qwen2.5-Coder models
- [RFC]: Prefill-only optimizations for PD disaggregation in vLLM
- [RFC]: Elastic Expert Parallelism
- [Bug]: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.1%, Prefix cache hit rate: 11.9%
- [feat] preserve metadata for quantized model weight reload
- [Performance]: Compiled `QuantFP8.forward_native` group quantization (1, 128) slower than CUDA on H100/RTX5090
- [RFC]: Enable libtorch-ABI-stable vLLM cuda wheels
- Docs
- Python not yet supported