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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Enable FP8 KV-cache and relax constraints for RDNA4 custom paged attention
- [Bug]: Improve `--kv-cache-dtype` behavior when checkpoint specifies `kv_cache_quant_algo`
- [Feature]: parity with cuda - ROCm Kimi K2.5 disagg PD +wideEP recipe
- [WIP][Bugfix] Wire whitespace_pattern through V1 structured output backends
- [ROCm][Kernel] Add fused MoE exllama GEMM for compressed-tensors int4
- [Bug]: vLLM produces invalid UTF-8 tokens and “�” replacement characters when returning logprobs
- fix(spec): extend vocab size validation to MTP and Eagle methods
- [Bugfix] Step3p5 reasoning end detection state leak in streaming chat
- Qwen3-Coder-Next-FP8 with tool calling causes system hard-freeze on multi-GPU tensor parallel (v0.15.1)
- [Bug]: nvidia/Llama-3.3-70B-Instruct-NVFP4 Degraded / Gibberish Output with TRITON_ATTN
- Docs
- Python not yet supported