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
- [Performance]: Why the avg. througput generation is low?
- [Feature]: Support W4A8KV4 Quantization(QServe/QoQ)
- [Feature]: Host CPU Docker image on Docker Hub
- [Bug]: multi-gpu for baichuan2-13B-Chat benchmark_serving
- [Performance]: Will memcpy happen with distributed kv caches while decoding ?
- [Usage]: how to use run in mixed mode CPU/GPU (device_map="auto")
- [Bug]: Running vllm docker image with neuron fails
- [Feature]: Build and publish Neuron docker image
- Add a new kernel for fusing the dequantization in fused-moe gemm
- [Misc]: Assertion with no scription in vllm with DeepSeekMath 7b model, why, how to fix?
- Docs
- Python not yet supported