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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: vLLM v0.22.1 in 8 * H20-3e 141G environment deploying DeepSeek-V4-Pro reports error "mlir_global_dtors() missing 1 required positional argument: 'data'".
- [WIP] Add Dynamic Context Parallelism for long-context serving
- [Bug]: vllm-0.22.0 fail to run "Qwen/Qwen3.5-9B" in offline `LLM` mode
- [Bug]: [ROCm][FLA] chunk_gated_delta_rule Triton compilation fails on MI210/gfx90a with num_stages=4
- [Metrics] Add vllm:request_received counter labeled by input modality
- perf: add push-based allreduce for small tensor reductions
- [ROCm][Kernel][AITER] BlockScale FP8 SplitK zero-init fusion
- [CPU][Zen] Route Int8 MoE inference through zentorch on AMD
- [Kernel][Perf] Add moe_sum_kernel specializations for topk=5-8
- [KV Offload] Reshape the transfer data model: per group specs and offloaded side alignment offset
- Docs
- Python not yet supported