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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- MulAndSilu rework for vLLM IR
- [Kernel][DSv4] Add sparse-gather variant of dequantize_and_gather_k_cache
- SiluAndMulWithClamp rework for vLLM IR
- Kimi NVFP4 specialized model
- [CI][AMD][BugFix] Set num_gpus=2 for trainer for distributed RL example
- [Bugfix] Treat max_tokens as upper bound, not input-space reservation
- [Bug]: Gemma 4 31B random drops in performance on H200 and B200 with 2 GPUs
- [Feature][KV Cache] Support excluding SWA layers from NVFP4 KV cache
- Create `test_kimi_k2_thinking_nvfp4.py` for accuracy check
- [Bug]: Distributed inference hanging on a 2 node DGX spark cluster with Mistral 3.5 Medium 128B with TP=2
- Docs
- Python not yet supported