The CUDA kernel for KV Cache quantization and dequantization for LLM
-
Notifications
You must be signed in to change notification settings - Fork 0
The CUDA kernel for KV Cache quantization and dequantization for LLM
License
wsxhjnb1/KVQuant
About
The CUDA kernel for KV Cache quantization and dequantization for LLM
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published