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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]:
- using Falconlite2 for vllm benchmarking
- [Bug]: Error executing method start_worker_execution_loop. This might cause deadlock in distributed execution.
- [Bug]: no GPU activity when SamplingParams argument `n` is set to > 200
- [Bug]: The Qwen2 model gives no response when the tensor_parallel_size is set to 1.
- [Bug]: TypeError: Object of type ModelMetaclass is not JSON serializable when using guided decoding
- hope that we can use multi-GPU directly in vllm for BitAndBytes quantization
- [Bug]: DeepSeek-V2-Lite quantized model raise model shape Error
- [Core] get_kv_cache_from_block within core ONLY
- [Bug]: Available context (gpu blocks) gets halved by pipeline parallel size
- Docs
- Python not yet supported