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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Quantization] Make activation-quantization fallbacks explicit, add VLLM_STRICT_QUANT_SCHEME
- [Kernel][Fusion] Fuse GELU-tanh+Mul with NVFP4 quantization (Gemma 2/3/4)
- [Bugfix] Fall back to the cached file list when the HF Hub is unreachable
- Consolidate speculative decoding correctness and acceptance tests
- [Bug]: Qwen3-Coder-Next AutoRound routed MoE gate ignores checkpoint quantization
- [Bug]: ThinkingBudgetStateHolder maps every request to logits row 0 when spec decoding is on but a step has no drafts
- [Bug]: ThinkingBudgetStateHolder.sync_batch leaks stale state on unidirectional moves
- [Bugfix][Kernel] Keep batch x heads out of gridDim.z in the shared FLA recurrent kernels
- [Core] Opt-in per-request return of the last hidden states in generation (MRV2)
- [Bug]: GLM-5.3 NVFP4 with DCP and MTP does not start on Hopper on main (DSA MTP head, DCP a2a default)
- Docs
- Python not yet supported