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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Fix shuffled KV-cache writes for hybrid attention layouts
- [Feature]: Tri-attention merge?
- [Bugfix] Narrow fp8_e5m2 kv-cache gate to only reject actual fp8 checkpoints
- [Bug]: NCCL Error: unhandled cuda error
- [Security] Unpinned Third-Party GitHub Action in macOS Workflow
- `--reasoning-config` breaks Nemotron v3 reasoning parser (content always null, thinking unbounded)
- [Bug]: HFValidationError when loading model from cloud storage (s3://) with `HF_HUB_OFFLINE=1`
- [Bug]: fp8_e5m2 kv-cache gate in _init_kv_cache_quant fires on any quantized checkpoint, not only fp8 checkpoints
- [Bug]: Segfault in Triton LLVM (MachineCSE / translateLLVMIRToASM) when serving Qwen3.5-4B on RTX 4090 (WSL2) with vLLM 0.19.0
- [RFC][Test]: Unified Platform-Aware Test Skip Mechanism
- Docs
- Python not yet supported