Add ROCm/AMD detection: use SDPA backend instead of flash_attn - #28
Open
WakeUpMorty wants to merge 1 commit into
Open
Add ROCm/AMD detection: use SDPA backend instead of flash_attn#28WakeUpMorty wants to merge 1 commit into
WakeUpMorty wants to merge 1 commit into
Conversation
- server.js: detect ROCm via ComfyUI /system_stats; rewrite node backend flash_attn -> sdpa at queue time (NVIDIA unchanged). - electron/comfysetup.cjs: allow ROCm in pickBuild, skip CUDA torch + flash-attn install, flip --use-flash-attention to --use-pytorch-cross-attention on ROCm. Based on https://github.com/WakeUpMorty/Trellis2-Rocm-Windows-Installer
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Based on https://github.com/WakeUpMorty/Trellis2-Rocm-Windows-Installer