Skip to content

GitLab

Unverified Commit 29f4151e authored by molamooo's avatar molamooo Committed by GitHub
Browse files

[fix] f16 dequantize device ignored

parent cbc47d0b
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
ktransformers/util/custom_gguf.py
View file @ 29f4151e
...@@ -681,7 +681,7 @@ def dequantize_f16_gpu(data, device): ...@@ -681,7 +681,7 @@ def dequantize_f16_gpu(data, device):
res = torch.from_numpy(data) res = torch.from_numpy(data)
res_gpu = torch.empty_like(res, device=device) res_gpu = torch.empty_like(res, device=device)
res_gpu.copy_(res) res_gpu.copy_(res)
return res return res_gpu
GGML_DEQUANTIZE = { GGML_DEQUANTIZE = {
"F32": dequantize_f32, "F32": dequantize_f32,
......
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