Skip to content

GitLab

Unverified Commit 0422152c authored by Atream's avatar Atream Committed by GitHub
Browse files

Merge pull request #670 from akemimadoka/fix-win 

Fix RuntimeError on Windows caused by integer overflow in np.prod
parents 798e1d0c 8817777e
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
ktransformers/util/custom_gguf.py
View file @ 0422152c
...@@ -27,6 +27,7 @@ import torch ...@@ -27,6 +27,7 @@ import torch
import KTransformersOps import KTransformersOps
from .custom_loader import SafeTensorLoader from .custom_loader import SafeTensorLoader
import ctypes import ctypes
import math
class GGMLQuantizationType(IntEnum): class GGMLQuantizationType(IntEnum):
F32 = 0 F32 = 0
...@@ -230,7 +231,7 @@ class GGUFLoader: ...@@ -230,7 +231,7 @@ class GGUFLoader:
shape = [read_value(f, DATA_TYPES["uint64"]) for _ in range(shape_len)] shape = [read_value(f, DATA_TYPES["uint64"]) for _ in range(shape_len)]
ggml_type = read_value(f, DATA_TYPES["uint32"]) ggml_type = read_value(f, DATA_TYPES["uint32"])
bad_offset = read_value(f, DATA_TYPES["uint64"]) bad_offset = read_value(f, DATA_TYPES["uint64"])
n_elems = int(np.prod(shape)) n_elems = int(math.prod(shape))
block_size, type_size = GGML_QUANT_SIZES[ggml_type] block_size, type_size = GGML_QUANT_SIZES[ggml_type]
n_bytes = n_elems * type_size // block_size n_bytes = n_elems * type_size // block_size
np_dims = tuple(reversed(shape)) np_dims = tuple(reversed(shape))
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment