tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-31 22:53:52 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/bitnet-ternary

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-07-28 21:27:33 -04:00
parent dd3e62a703 6eeaeba126
commit 79a278e922
340 changed files with 43840 additions and 162220 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/quants.py
View File

@@ -43,7 +43,7 @@ def __apply_over_grouped_rows(func: Callable[[np.ndarray], np.ndarray], arr: np.
osize *= dim
out = np.empty(shape=osize, dtype=otype)
# compute over groups of 16 rows (arbitrary, but seems good for performance)
n_groups = rows.shape[0] // 16
n_groups = (rows.shape[0] // 16) or 1
np.concatenate([func(group).ravel() for group in np.array_split(rows, n_groups)], axis=0, out=out)
return out.reshape(oshape)