tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 20:45:04 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,700 Commits 443 Branches 3,863 Tags
compilade/bitnet-ternary
Commit Graph

2 Commits

Author SHA1 Message Date
Francis Couture-Harpin
3a0bf17d57 gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0 
* ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0

This does not change anything for ternary models,
since their values should never end up being in halfway cases anyway.
 2024-08-12 00:06:48 -04:00
compilade
4134999e01 gguf-py : Numpy dequantization for most types (#8939) 
* gguf-py : Numpy dequantization for most types

* gguf-py : Numpy dequantization for grid-based i-quants
 2024-08-11 14:45:41 -04:00