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] Fix type-sensitive tool argument coercion
- [Bugfix] DeepSeek-V4 tokenizer: honor add_generation_prompt and continue_final_message
- Revert "[Hardware][AMD][CI] Fix e2e core test group" (#46024)
- [Bug]: PP2 tool calling produces garbled output while PP1 works correctly (GLM-5.2-FP8 DSA, chunked-prefill)
- [ROCm][Test] Resurrect test_rocm_mxfp4_moe_oracle
- [specdec][v1] Fix sampler peak memory profiling for speculative decoding (revives #38220)
- [Kernel] Add fused SiLU+Mul+PerTokenQuant CUDA kernel
- [Test] Add Qwen3 streaming tool-call regression tests across stream intervals
- [Bugfix] YaRN RoPE: honor explicit attention_factor from the rope config
- [Bugfix] Align hybrid model prefix cache hit lengths to prevent block missing on EAGLE
- Docs
- Python not yet supported