github/InvokeAI
1
1
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add inference tests for all custom module types (i.e. to test autocasting from cpu to device).

Browse Source
This commit is contained in:
Ryan Dick
2024-12-26 18:33:46 +00:00
parent 03944191db
commit a8b2c4c3d2
4 changed files with 200 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/backend/quantization/gguf/ggml_tensor.py
View File

@@ -48,11 +48,13 @@ GGML_TENSOR_OP_TABLE = {
# Ops to run on the quantized tensor.
torch.ops.aten.detach.default: apply_to_quantized_tensor, # pyright: ignore
torch.ops.aten._to_copy.default: apply_to_quantized_tensor, # pyright: ignore
torch.ops.aten.clone.default: apply_to_quantized_tensor, # pyright: ignore
# Ops to run on dequantized tensors.
torch.ops.aten.t.default: dequantize_and_run, # pyright: ignore
torch.ops.aten.addmm.default: dequantize_and_run, # pyright: ignore
torch.ops.aten.mul.Tensor: dequantize_and_run, # pyright: ignore
torch.ops.aten.add.Tensor: dequantize_and_run, # pyright: ignore
torch.ops.aten.allclose.default: dequantize_and_run, # pyright: ignore
}
if torch.backends.mps.is_available():