llama.cpp
76f186df
- ggml : IQ2 creation speedup through caching (#31910)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
8 hours ago
ggml : IQ2 creation speedup through caching (#31910) * IQ2 quant creation speedup from caching * Rename variables for clarity * Explicit casts * Initialize all values, add comment to tolerance
References
#31910 - IQ2 creation speedup through caching
Author
bartowski1182
Parents
95b09b62
Loading