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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: KeyError: 'language_model.model.layers.20.linear_attn'
- cumem allocator: double-free and stale error codes during sleep/wake cycles
- [Bug]: Frequent Tool Call Parsing Failures with DeepSeek-V3.2
- [Bug]: Garbled output Qwen3.5-122B-A10B VLLM 0.17.0
- [RFC]: Dynamic Speculation Length (DSL) with Confidence-Threshold Early Exit for vLLM Speculative Decoding
- [Bug]: Duplicate token with different logprob when requesting top
- [Bug]: CUBLAS_STATUS_INVALID_VALUE in Docker due to LD_LIBRARY_PATH cuBLAS version conflict
- [Bug]: Qwen3.5 AWQ models crash during inference on RTX 5090 (Blackwell) with Triton OOM in solve_tril despite successful model load
- [Bugfix] Fix cpu-offload-gb assertion with non-default block sizes
- [Bug]: Qwen3.5-27B fails to start with CPU KV cache offloading (`--kv_offloading_backend native`) while Qwen3-32B works fine
- Docs
- Python not yet supported