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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Qwen3-235B-Instruct-MTP fails to parse the response while a chunk includes multiple tokens
- [Feature]: any plan to support Relaxed Acceptance in v1?
- Add `moe_align_block_size_no_permute` for small batch size with large num_expert
- [Bug]:fused_moe_lora_op compile error
- [Bug]: DSR1 NVFP4 DEP cannot run because assert batch_descriptor.num_tokens == num_tokens_padded
- [WIP] Bump dockerfile to cuda 13.0.2 (for testing)
- fix(nemotron_h): Add missing rotary positional embeddings to attention layers
- [Bug]: GPT-OSS-120B returns null content when hitting max_tokens without --enforce-eager
- [Bug]: Fail to run Qwen3-Next-80B-A3B-Instruct vllm with CPU backend
- [Bug]: CUDA Illegal Memory Access when running Qwen3-Next-80B-A3B-Instruct on 4xB200 GPUs
- Docs
- Python not yet supported