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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(moe): detect and handle unquantized MoE weights in NVFP4 checkpoints
- [Bugfix][sleepmode] Serialize GPU VMM operations to fix sleep/wakeup race condition
- [Feature][Cleanup]: Optimize token data structures (list[int] to TokenArray)
- feat: Standardize load_weights API via AutoWeightsLoader
- [RFC]: Observation Plugin for Intercepting & Routing on Activations
- [RFC]: Context-Aware KV-Cache Retention API (Prioritized Evictions)
- [Bug]: GPT-OSS-120B gpt-oss MXFP4 on SM121 (Blackwell DGX Spark): Marlin kernel generates wrong first Harmony token, producing null content/reasoning
- [Bug]: cudaErrorIllegalAddress in gdn_attn.py:237 when using qwen3_next_mtp with num_speculative_tokens=5 under load
- fix: add "context_length_exceeded" error code to match OpenAI convention
- fix: generalize LoRA layer handling for N-way fused projections
- Docs
- Python not yet supported