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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix spawn_new_process_for_each_test silently swallowing test failures
- [Bug]: Gemma-4 31B with DFlash speculator produces gibberish/repetitive token loop
- [Feature]: Update default Python version in pre-built docker images
- [Performance]: Encode performance of vLLM
- [Feature]: Helion Kernels for MLA (Decode)
- [Bug] Gemma 4 31B crashes on k_eq_v full-attention layers (QKV split shape mismatch)
- [Bug]: Unable to use ibm-granite/granite-speech-4.1-2b with vllm 0.20.0
- [Feature]: Migration from Model Runner v1 to Model Runner v2
- [Bug]: V1 + Ray multi-node pipeline parallel `KeyError` at KV-cache init due to missing `global_rank` update
- [ROCm][CI] Fix and stabilize EAGLE3 acceptance tests
- Docs
- Python not yet supported