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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [V1][DP][LB] Publish request counts at the start of each engine step
- [Bugfix][GLM-4] Skip schema injection for Responses named-function
- [EPLB] Niixl communicator optimization. Zero-copy transfers
- 📝 Integration Proposal: CAJAL — Scientific Paper Model Serving
- [Bug]: FlashInfer attention + FP8 KV cache + CUDA graphs produces random output on RTX 6000 Pro Blackwell (sm_120); TRITON_ATTN backend works
- [Quantization] add humming moe backend to all fused moe oracles
- [Build] Switch CUDA 12.9 wheel builds to PyTorch manylinux_2_28 base
- [ROCm][CI] Remove benchmarks test group and shard long test groups
- Layerwise reload crashes with CUDA illegal memory access on compressed-tensors channel-wise FP8 MoE
- [Bug]: thinking_token_budget silently ignored when no penalties are set (inverted condition in gpu_input_batch.py)
- Docs
- Python not yet supported