wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-12-16 01:37:04 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

I found a case where this is needed (#10875)
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Details
Python Linting / Run Pylint (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Details
Execution Tests / test (macos-latest) (push) Waiting to run
Details
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Details
Execution Tests / test (windows-latest) (push) Waiting to run
Details
Test server launches without errors / test (push) Waiting to run
Details
Unit Tests / test (macos-latest) (push) Waiting to run
Details
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Details
Unit Tests / test (windows-2022) (push) Waiting to run
Details

Browse Source
This commit is contained in:
comfyanonymous 2025-11-25 00:23:19 -08:00 committed by GitHub
parent acfaa5c4a1
commit 015a0599d0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
comfy/quant_ops.py
View File

@ -405,8 +405,8 @@ class TensorCoreFP8Layout(QuantizedLayout):
tensor_scaled = tensor * (1.0 / scale).to(tensor.dtype) tensor_scaled = tensor * (1.0 / scale).to(tensor.dtype)
# TODO: uncomment this if it's actually needed because the clamp has a small performance penality' # TODO: uncomment this if it's actually needed because the clamp has a small performance penality'
# lp_amax = torch.finfo(dtype).max lp_amax = torch.finfo(dtype).max
# torch.clamp(tensor_scaled, min=-lp_amax, max=lp_amax, out=tensor_scaled) torch.clamp(tensor_scaled, min=-lp_amax, max=lp_amax, out=tensor_scaled)
qdata = tensor_scaled.to(dtype, memory_format=torch.contiguous_format) qdata = tensor_scaled.to(dtype, memory_format=torch.contiguous_format)
layout_params = { layout_params = {