vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-09 22:05:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[fix] f16 dequantize device ignored

Browse source
This commit is contained in:
molamooo 2024-08-22 15:10:06 +08:00 • committed by GitHub
parent cbc47d0b68
commit 29f4151ebc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/util/custom_gguf.py
View file

@ -681,7 +681,7 @@ def dequantize_f16_gpu(data, device):
res = torch.from_numpy(data)
res_gpu = torch.empty_like(res, device=device)
res_gpu.copy_(res)
return res
return res_gpu
GGML_DEQUANTIZE = {
"F32": dequantize_f32,