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
- [Bug] DFlash speculative decoding fundamentally incompatible with all KV cache quantization (fp8, turboquant) due to non-causal attention requirement
- [Feature]: Close all non gpustack related tickets and route them to provider`s github
- [Feature]: Polymorphic buffer management for V1 worker (CPU/GPU staged tensors, lower hot-path overhead)
- [Bug]: Decode Context Parallelism (`--decode-context-parallel-size`) output drift and gibberish in latest nightly
- [V1][DP][LB] Publish request counts at the start of each engine step
- [Bugfix][GLM-4.7] Skip schema injection for Responses named-function
- [EPLB] Niixl communicator optimization. Zero-copy transfers
- [Bug]: gpt-oss MoE moe_forward fake-kernel shape mismatch breaks torch.compile + TP > 1 on Blackwell
- 📝 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
- Docs
- Python not yet supported