onnxruntime
KV cache quantization for ORT WebGPU
#28059
Merged

KV cache quantization for ORT WebGPU #28059

sushraja-msft merged 3 commits into main from user/sushraja/turbo_quant
sushraja-msft
sushraja-msft sushraja-msft changed the title User/sushraja/turbo quant WIP: Turbo quant for ORT WebGPU 119 days ago
sushraja-msft sushraja-msft marked this pull request as draft 119 days ago
github-actions
github-actions commented on 2026-04-14
github-advanced-security
github-advanced-security commented on 2026-04-14
sushraja-msft sushraja-msft changed the title WIP: Turbo quant for ORT WebGPU WIP: TurboQuant for ORT WebGPU 119 days ago
sushraja-msft sushraja-msft force pushed from 6bd20020 to 74ba45aa 68 days ago
github-advanced-security
github-advanced-security commented on 2026-06-04
github-actions
github-actions commented on 2026-06-04
github-actions
github-actions commented on 2026-06-06
sushraja-msft sushraja-msft force pushed from ae56ae6d to fb35f72d 60 days ago
github-actions
github-actions commented on 2026-06-12
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 60 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-12
sushraja-msft sushraja-msft force pushed from 1ba7ddf1 to e5945225 58 days ago
github-advanced-security
github-advanced-security commented on 2026-06-13
github-actions
github-actions commented on 2026-06-13
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 58 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-13
sushraja-msft sushraja-msft force pushed from 1e837ac6 to 24089cb7 56 days ago
sushraja-msft sushraja-msft marked this pull request as ready for review 56 days ago
sushraja-msft sushraja-msft assigned guschmue guschmue 56 days ago
sushraja-msft sushraja-msft assigned qjia7 qjia7 56 days ago
sushraja-msft sushraja-msft changed the title WIP: TurboQuant for ORT WebGPU TurboQuant style KV cache compression for ORT WebGPU 56 days ago
qjia7
qjia7 commented on 2026-06-18
sushraja-msft sushraja-msft force pushed from 24089cb7 to 745ddbec 49 days ago
github-actions
github-actions commented on 2026-06-23
sushraja-msft sushraja-msft force pushed from bfa03fce to 89d0b1a8 49 days ago
sushraja-msft
guschmue
sushraja-msft sushraja-msft force pushed from 4fd53925 to e3f0cd05 47 days ago
sushraja-msft sushraja-msft changed the title TurboQuant style KV cache compression for ORT WebGPU KV cache quantization for ORT WebGPU 47 days ago
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 47 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-25
qjia7
qjia7 dismissed these changes on 2026-06-25
sushraja-msft sushraja-msft dismissed their stale review via 7ec6d895 46 days ago
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 46 days ago
sushraja-msft
sushraja-msft sushraja-msft closed this 46 days ago
sushraja-msft sushraja-msft reopened this 46 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-25
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 46 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-25
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 46 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-26
github-actions
github-actions commented on 2026-06-26
sushraja-msft sushraja-msft requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 46 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-26
sushraja-msft Turbo Quant: WebGPU KV cache quantization (squashed)
1380f413
sushraja-msft rebase - fixup
22f1b1ad
sushraja-msft sushraja-msft force pushed from 90d859f6 to 22f1b1ad 45 days ago
github-actions
github-actions commented on 2026-06-27
sushraja-msft fix test
b1b0bdf4
qjia7
qjia7 approved these changes on 2026-06-29
sushraja-msft sushraja-msft merged d9fcce02 into main 42 days ago
sushraja-msft sushraja-msft deleted the user/sushraja/turbo_quant branch 42 days ago

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone