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
- [Model][Transformers backend] Fuse q/k/v and gate/up linear groups
- [Bug]: `trtllm_bf16_moe` FI autotune crashes with `illegal memory access` when `--enforce-eager` is set
- [Frontend] Add the p-less Sampling Method for LLM Decoding
- [Bugfix] Hermes tool parser: parse tool call JSON by object boundary, not literal </tool_call>
- [Security] Centralize grammar compilation timeout at scheduler level
- [RFC]: Extend hidden-state extraction to export verifier KV caches
- [Misc] Add support for passing intermediate tensors for KV cache optimization research
- [Bugfix] Reject negative config limits
- [Quantization] Fix misleading NVFP4 Marlin MoE fallback warning on GPUs with native FP4
- XPU: replicate Mamba2 in_proj scales when n_groups<tp_size
- Docs
- Python not yet supported