Skip to content

Added LongRoPe Model Causal Mask Pattern Fusion #2473

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

Draft
wants to merge 29 commits into
base: main
Choose a base branch
from
Draft

Added LongRoPe Model Causal Mask Pattern Fusion #2473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
29 commits
Select commit Hold shift + click to select a range
7bd391d
Added Causal Mask Pattern Fusion for LongRoPe Models
tadani3 Jul 24, 2025
f0f41a8
Added Phi4-mini-reasoning cache insertion and position Id deletion logic
tadani3 Jul 31, 2025
189d0c8
Merge branch 'main' into longrope_causal_mask
tadani3 Jul 31, 2025
758e92d
Removed whitespace from gqa longrope fusion
tadani3 Aug 1, 2025
d4a8c57
Added docstrings to GQA pattern method
tadani3 Aug 1, 2025
30faab7
Renamed pattern branches to match kv_range, query_range, and batch_ra…
tadani3 Aug 1, 2025
01e37b3
Merge branch 'longrope_causal_mask' of https://github.com/tadani3/onn…
tadani3 Aug 1, 2025
912a80b
Removed unecessary pattern variable
tadani3 Aug 1, 2025
fd95719
Added snake casing for variable names
tadani3 Aug 1, 2025
19d2656
Added more snake casing and removed uneeded code
tadani3 Aug 1, 2025
0742db2
Moved get_mask_key method to module level and used IR value directly
tadani3 Aug 1, 2025
2772f77
Added cleanup method for the attention mask cache
tadani3 Aug 1, 2025
87a0464
Added LongRoPE GQA Causal Mask Fusion Separately
tadani3 Aug 1, 2025
f12630c
Removed whitespace from gqa longrope fusion
tadani3 Aug 1, 2025
7519653
Added docstrings to GQA pattern method
tadani3 Aug 1, 2025
e59cb83
Renamed pattern branches to match kv_range, query_range, and batch_ra…
tadani3 Aug 1, 2025
bad7811
Remove DORT related tests since it was removed from PyTorch (#2465)
justinchuby Jul 24, 2025
19f5e65
Handle matching against None explicitly (#2460)
gramalingam Jul 25, 2025
17c117f
[docs] Document rewriter pattern options (#2406)
Copilot Jul 30, 2025
3fb87c0
Update requirements-ort-nightly.txt (#2471)
justinchuby Jul 31, 2025
127aee8
Fix logic for converting np array to text (#2470)
justinchuby Jul 31, 2025
131e497
[torchlib] Improves aten_chunk conversion (#2469)
justinchuby Jul 31, 2025
acdfd1b
Removed unecessary pattern variable
tadani3 Aug 1, 2025
76624ad
Added snake casing for variable names
tadani3 Aug 1, 2025
fbb191a
Added more snake casing and removed uneeded code
tadani3 Aug 1, 2025
f295bc5
Moved get_mask_key method to module level and used IR value directly
tadani3 Aug 1, 2025
0334bb1
Added cleanup method for the attention mask cache
tadani3 Aug 1, 2025
74e8e24
Added LongRoPE GQA Causal Mask Fusion Separately
tadani3 Aug 1, 2025
d5383f0
Merge branch 'longrope_attention_causal_mask' of https://github.com/t…
tadani3 Aug 1, 2025
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
Loading
Loading