Skip to content

ComfyUI: Updated gfx110X Windows ROCm nightly index. Added Win-ROCm EnVars #1524

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mohnjiles merged 1 commit into from
Jan 19, 2026
+4 −2
Merged

ComfyUI: Updated gfx110X Windows ROCm nightly index. Added Win-ROCm EnVars #1524

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions StabilityMatrix.Core/Models/Packages/ComfyUI.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -382,7 +382,7 @@ await StandardPipInstallProcessAsync(
var indexUrl = gfxArch switch
{
"gfx1151" => "https://rocm.nightlies.amd.com/v2/gfx1151",
_ when gfxArch.StartsWith("gfx110") => "https://rocm.nightlies.amd.com/v2/gfx110X-dgpu",
_ when gfxArch.StartsWith("gfx110") => "https://rocm.nightlies.amd.com/v2/gfx110X-all",
_ when gfxArch.StartsWith("gfx120") => "https://rocm.nightlies.amd.com/v2/gfx120X-all",
_ => throw new ArgumentOutOfRangeException(
nameof(gfxArch),
Expand Down Expand Up @@ -870,6 +870,8 @@ private ImmutableDictionary<string, string> GetEnvVars(ImmutableDictionary<strin
// set some experimental speed improving env vars for Windows ROCm
return env.SetItem("PYTORCH_TUNABLEOP_ENABLED", "1")
.SetItem("MIOPEN_FIND_MODE", "2")
.SetItem("TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL", "1");
.SetItem("TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL", "1")
.SetItem("PYTORCH_ALLOC_CONF", "max_split_size_mb:6144,garbage_collection_threshold:0.8") // greatly helps prevent GPU OOM and instability/driver timeouts/OS hard locks and decreases dependency on Tiled VAE at standard res's
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Jan 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This line contains magic numbers (6144, 0.8) and a very long comment, which can impact readability and maintainability.

I recommend extracting the numeric values into named constants to make their purpose explicit and easier to modify in the future. For example:

private const int PytorchAllocMaxSplitSizeMb = 6144;
private const double PytorchAllocGcThreshold = 0.8;

Additionally, the comment should be wrapped to fit within standard line length limits. I've provided a suggestion for reformatting the comment. Please consider applying the constants as well.

            // Greatly helps prevent GPU OOM, instability, driver timeouts, and OS hard locks.
            // It also decreases dependency on Tiled VAE at standard resolutions.
            .SetItem("PYTORCH_ALLOC_CONF", "max_split_size_mb:6144,garbage_collection_threshold:0.8")

.SetItem("COMFYUI_USE_MIOPEN", "1"); // re-enables "cudnn" in ComfyUI as it's needed for MiOpen to function properly
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Jan 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This comment is quite long and makes the line exceed typical length recommendations. For better readability, it's good practice to place comments on their own line(s) above the code they refer to, especially when they are descriptive.

            // Re-enables "cudnn" in ComfyUI as it's needed for MIOpen to function properly.
            .SetItem("COMFYUI_USE_MIOPEN", "1");

}
}
Loading