-
Notifications
You must be signed in to change notification settings - Fork 54
Issues: NVIDIA/Fuser
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Inlining error in Hopper matmul with AxisMapping and grid swizzling
Matmuls
#3671
opened Jan 6, 2025 by
jacobhinkle
pad on broadcast dimensions hitting assert during transform replay
#3660
opened Dec 31, 2024 by
jjsjann123
Feature request: Extend the uop forwarding in the fusion segmenter to include other single-input trivial ops
rope
#3647
opened Dec 25, 2024 by
naoyam
Feature request: Schedule a small matmul op as a reduction (or pointwise) op
rope
#3646
opened Dec 25, 2024 by
naoyam
Feature request: Extend the remove broadcast + squeeze pass
rope
#3635
opened Dec 23, 2024 by
naoyam
Performance gap between manual nvfuser definition and
thunder.jit
#3629
opened Dec 20, 2024 by
Priya2698
Python segmentation failure with resize
Python API
Issues related to the Python API
Segmentation
Issues related to nvFuser Segmentation
#3594
opened Dec 16, 2024 by
naoyam
TesnsorDomain::allIDs() miss additional IDs introduced by setLoopDomain
#3571
opened Dec 11, 2024 by
naoyam
transpose scheduler should have its own reference_tv validation logic
#3570
opened Dec 11, 2024 by
jjsjann123
Why do we have 3.7x TMA instructions compared to cuBLAS?
Matmuls
#3569
opened Dec 11, 2024 by
zasdfgbnm
The Segmenter Logic Latency increases 10x between 20 and 30 Fusions
Host Latency
Segmentation
Issues related to nvFuser Segmentation
Thunder
#3510
opened Dec 2, 2024 by
kevinstephano
Reduce nvFuser's Hot Path Host Latency
Host Latency
perf
Thunder
#3507
opened Dec 2, 2024 by
kevinstephano
Previous Next
ProTip!
Adding no:label will show everything without a label.