From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sat, 27 Jul 2024 07:55:01 +0200 Subject: Merge mainline llama.cpp (#3) * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow --- gguf-py/gguf/quants.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'gguf-py/gguf/quants.py') diff --git a/gguf-py/gguf/quants.py b/gguf-py/gguf/quants.py index b22eec16..16e0a9aa 100644 --- a/gguf-py/gguf/quants.py +++ b/gguf-py/gguf/quants.py @@ -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) -- cgit v1.2.3