onnxruntime
Add GQA workspace estimation
#32617
Merged
Overview
Commits
12
Changes
View On GitHub

Add GQA workspace estimation #32617

titaiwangms merged 12 commits into microsoft:main from titaiwangms:titaiwangms/gqa-workspace-estimation
titaiwangms
titaiwangms titaiwangms marked this pull request as ready for review 5 days ago
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 5 days ago
titaiwangms titaiwangms added ep:CUDA
titaiwangms titaiwangms added memory
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-15
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 5 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-15
titaiwangms titaiwangms force pushed from 39eb9f91 to e2480024 4 days ago
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 4 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-16
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 4 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-16
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 4 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-16
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 4 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-16
titaiwangms titaiwangms requested a review from chilo-ms chilo-ms 4 days ago
chilo-ms
titaiwangms titaiwangms force pushed from 34e847cf to fd857157 3 days ago
titaiwangms
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 3 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-17
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 3 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-17
chilo-ms
chilo-ms
chilo-ms dismissed these changes on 2026-09-17
titaiwangms titaiwangms dismissed their stale review via 5bdd4798 3 days ago
titaiwangms
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 3 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-17
titaiwangms titaiwangms enabled auto-merge (squash) 3 days ago
chilo-ms
chilo-ms approved these changes on 2026-09-17
Copilot Add GQA workspace estimation
60429e53
Copilot Harden GQA workspace bounds
1e6add3a
Copilot Clarify GQA workspace bound contracts
fd5a2fe6
Copilot Test GQA Level-2 workspace declaration
ff30fd64
Copilot Fix GQA partial rotary estimation
a7271ad2
Copilot Match GQA estimator cache geometry
44ee6fd9
Copilot Test GQA Level-1 budget integration
2924e210
Copilot Fix GQA budget test thresholds
1379b86b
Copilot Account for prepacked GQA head sink
72f42a06
Copilot Conservatively account for disabled GQA prepacking
07a61dfa
Copilot Harden GQA prepack lifetime accounting
f5716ad4
Copilot Test GQA Level-1 lifetime propagation
9bd7af2d
titaiwangms titaiwangms force pushed from 5bdd4798 to 9bd7af2d 3 days ago
titaiwangms titaiwangms requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 3 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-17
titaiwangms titaiwangms merged bc8e7ed7 into main 3 days ago
titaiwangms titaiwangms deleted the titaiwangms/gqa-workspace-estimation branch 3 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
ep:CUDA memory
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum