forked from onnx/optimizer
-
Notifications
You must be signed in to change notification settings - Fork 0
Pull requests: onnxsim/optimizer
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
cse_util.h: bound CSETensorHash's raw_data hash cost for large tensors
#15
opened Aug 26, 2026 by
take-cheeze
Member
Loading…
3 tasks done
extract_constant_to_initializer: move the Tensor into the new initializer
#14
opened Aug 25, 2026 by
take-cheeze
Member
Loading…
3 tasks done
Bridge Python3_INCLUDE_DIRS when only the unversioned Python module was found
#13
opened Aug 25, 2026 by
take-cheeze
Member
Loading…
1 of 2 tasks
extract_constant_to_initializer: batch-reserve names instead of one scan per match
#12
opened Aug 20, 2026 by
take-cheeze
Member
Loading…
3 tasks done
eliminate_deadend/eliminate_common_subexpression: avoid uses()'s O(N) capture scan
#11
opened Aug 20, 2026 by
take-cheeze
Member
Loading…
3 tasks done
Cache CSETensorHash's raw_data hash by tensor_id(), the actual bottleneck
#10
opened Aug 19, 2026 by
take-cheeze
Member
Loading…
Avoid ParseTensorData's double copy in CSE tensor hash/equality for raw_data
#8
opened Aug 18, 2026 by
take-cheeze
Member
Loading…
Fusions for onnxsim node-count parity: ConvTranspose, no-op Dropout, Unsqueeze & batched Gemm
#7
opened Jul 31, 2026 by
take-cheeze
Member
Loading…
Add fuse_matmul_add_bias_into_gemm_batched pass
#6
opened Jul 29, 2026 by
take-cheeze
Member
Loading…
Add option to treat initializers as non-constants
#2
opened Jul 29, 2026 by
take-cheeze
Member
Loading…
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.