llama.cpp
8e6fff84
- TP: quantized KV cache support (#23792)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 day ago
TP: quantized KV cache support (#23792) * TP: quantized KV cache support * fix partial view * remove overly strict assert
References
#23792 - TP: quantized KV cache support
Author
JohannesGaessler
Parents
02a57017
Loading