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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Perf] Dispatch Kimi-K3 KDA group64 projection
- [KV Offload] Allow replicated MLA layout for multi-group caches
- [Installation]:vllm-openai:kimi-k3 cpuoffloadgb not support?
- [Bugfix] Fix MoRIIO pending ACK resource exhaustion vulnerability
- [Bugfix][Parser] Preserve token IDs in non-streaming engine parsing
- [Bugfix][Benchmarks] Count tokens, not chunks, in peak output throughput
- [Bug]: Qwen3.6-35B-A3B produces corrupted output with EP and sequence parallelism enabled
- [transformers-utils] Only load dynamic module when trust_remote_code resolves to True
- [Bugfix] Fix Qwen3Next MoE sequence-parallel layout tracking
- Hybrid multi-group KV: _update_requests_with_invalid_blocks crashes (too many values to unpack) on connector load-error blocks
- Docs
- Python not yet supported