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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(ngram): sync ngram_gpu acceptance rate to match CPU
- fix(ngram): match async ngram_gpu acceptance rate to CPU
- Int4 kivi kv cache
- [Bug]: Unable to start Nemotron NVFP4 on 5090 after upgrade to vLLM 0.22
- [Bugfix] Fix integer overflow in libtorch_stable/layernorm_kernels.cu pointer arithmetic
- [Bugfix] DeepSeek V4: skip expert tensor when no mapping succeeds (AMD + NVIDIA)
- [Bugfix][Tool Parsers] Validate JSON arguments in extract_tool_calls for Kimi K2, DeepSeek V3/V3.1
- [Kernel][Helion][1/N] Add Helion kernel for fused_qk_norm_rope
- Add speculative decoding metrics
- [Bugfix] Reject negative values for max_logprobs and long_prefill_token_threshold
- Docs
- Python not yet supported