llama.cpp
897caccd
- fixes : speculative KV cache + llama worst-case graph
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
fixes : speculative KV cache + llama worst-case graph
References
#3228 - llama : custom attention mask + parallel decoding + no context swaps
Author
ggerganov
Committer
ggerganov
Parents
466b5138
Loading