Comfy-Org/wheels
1
0
Fork 0
mirror of https://github.com/Comfy-Org/wheels.git synced 2026-11-05 00:17:42 +00:00
Code Issues 7 Projects Packages Wiki Activity

[GH-ISSUE #10] FlashAttention 3 #3

New issue
Open
opened 2026-10-26 22:02:08 +00:00 by bsakaguchi · 1 comment
bsakaguchi commented 2026-10-26 22:02:08 +00:00
Owner
Copy link

Originally created by @woct0rdho on GitHub (Apr 15, 2026).
Original GitHub issue: https://github.com/Comfy-Org/wheels/issues/10

FlashAttention 3 exists and surprisingly not many people know it. It's mainly advertised to be fast on sm90 (H100), and in my benchmarks it's indeed a bit faster than FA2 on sm86 (RTX 3080), so it helps on consumer GPUs.

Some FA3 wheels are available at https://download.pytorch.org/whl/flash-attn-3/ . See the discussion in https://github.com/Dao-AILab/flash-attention/pull/2223 . The only thing missing is that they could not build wheel with Windows + cu130, and it has been fixed with the patch in https://github.com/windreamer/flash-attention3-wheels . This is worth tracking for us.

After we have the wheels, we can replace FA2 with FA3 on supported GPUs in ComfyUI.

Originally created by @woct0rdho on GitHub (Apr 15, 2026). Original GitHub issue: https://github.com/Comfy-Org/wheels/issues/10 FlashAttention 3 exists and surprisingly not many people know it. It's mainly advertised to be fast on sm90 (H100), and in my benchmarks it's indeed a bit faster than FA2 on sm86 (RTX 3080), so it helps on consumer GPUs. Some FA3 wheels are available at https://download.pytorch.org/whl/flash-attn-3/ . See the discussion in https://github.com/Dao-AILab/flash-attention/pull/2223 . The only thing missing is that they could not build wheel with Windows + cu130, and it has been fixed with the patch in https://github.com/windreamer/flash-attention3-wheels . This is worth tracking for us. After we have the wheels, we can replace FA2 with FA3 on supported GPUs in ComfyUI.
bsakaguchi commented 2026-10-26 22:02:09 +00:00
Author
Owner
Copy link

@PixWizardry commented on GitHub (Apr 18, 2026):

I am running below environment, I tried the closes WHL from windreamer:
"flash_attn_3-3.0.0+20260330.cu130torch2110cxx11abitrue.98024f-cp39-abi3-win_amd64.whl"

but ended up with an error:
"flash_attn_3 failed to import: dynamic module does not define module export function (PyInit__C). Falling back to native attention."

Environment:
Python version: 3.13.11
Platform: Windows 11
PyTorch version: 2.11.0+cu130
CUDA version: 13.0
NVIDIA RTX PRO 6000 Blackwell
ComfyUI 0.19.2

<!-- gh-comment-id:4274097053 --> @PixWizardry commented on GitHub (Apr 18, 2026): I am running below environment, I tried the closes WHL from windreamer: "flash_attn_3-3.0.0+20260330.cu130torch2110cxx11abitrue.98024f-cp39-abi3-win_amd64.whl" but ended up with an error: "flash_attn_3 failed to import: dynamic module does not define module export function (PyInit__C). Falling back to native attention." Environment: Python version: 3.13.11 Platform: Windows 11 PyTorch version: 2.11.0+cu130 CUDA version: 13.0 NVIDIA RTX PRO 6000 Blackwell ComfyUI 0.19.2
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
dependabot/github_actions/actions/setup-python-7.0.0
dependabot/github_actions/actions/checkout-7.0.1
dependabot/github_actions/actions/attest-build-provenance-4.1.1
dependabot/github_actions/peaceiris/actions-gh-pages-4.1.0
gh-pages
develop
torch_generic_nms-latest
sageattn3-latest
sageattention-latest
cc_torch-latest
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
Comfy-Org/wheels#3
No description provided.