Skip to content

Actions: pytorch/executorch

Actions

Test WebGPU Backend

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
test-backend-webgpu.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Arm backend: Fix Vulkan data graph shader module feature negotiation Test WebGPU Backend #14767: Pull request #22679 synchronize by wwwind
38m 8s wwwind:fix_feature
wwwind:fix_feature
38m 8s
Arm backend: Fix Vulkan data graph shader module feature negotiation Test WebGPU Backend #14766: Pull request #22679 opened by wwwind
36m 55s wwwind:fix_feature
wwwind:fix_feature
36m 55s
[executorch][muse-glimmer] Add unified CUDA sample_token entry point Test WebGPU Backend #14765: Pull request #22490 synchronize by Gasoonjia
37m 53s gh/Gasoonjia/13/head
gh/Gasoonjia/13/head
37m 53s
[executorch][muse-glimmer] Add CUDA sampling probabilities Test WebGPU Backend #14764: Pull request #22485 synchronize by Gasoonjia
36m 48s gh/Gasoonjia/8/head
gh/Gasoonjia/8/head
36m 48s
[executorch][muse-glimmer] Add CUDA speculative acceptance Test WebGPU Backend #14763: Pull request #22487 synchronize by Gasoonjia
36m 51s gh/Gasoonjia/10/head
gh/Gasoonjia/10/head
36m 51s
[executorch][muse-glimmer] Add CUDA residual correction sampling Test WebGPU Backend #14762: Pull request #22489 synchronize by Gasoonjia
37m 53s gh/Gasoonjia/12/head
gh/Gasoonjia/12/head
37m 53s
[executorch][muse-glimmer] Add CUDA categorical sampling Test WebGPU Backend #14761: Pull request #22486 synchronize by Gasoonjia
37m 31s gh/Gasoonjia/9/head
gh/Gasoonjia/9/head
37m 31s
[executorch][muse-glimmer] Add CUDA speculative sampling orchestration Test WebGPU Backend #14760: Pull request #22491 synchronize by Gasoonjia
37m 19s gh/Gasoonjia/14/head
gh/Gasoonjia/14/head
37m 19s
[executorch][muse-glimmer] Run DFlash sampling on CUDA Test WebGPU Backend #14759: Pull request #22678 opened by Gasoonjia
35m 54s gh/gasoonjia/183/head
gh/gasoonjia/183/head
35m 54s
[executorch][muse-glimmer] Add CUDA excluded-token correction Test WebGPU Backend #14758: Pull request #22677 opened by Gasoonjia
35m 26s gh/gasoonjia/182/head
gh/gasoonjia/182/head
35m 26s
[executorch][muse-glimmer] Add CUDA argmax sampling primitive Test WebGPU Backend #14757: Pull request #22676 opened by Gasoonjia
34m 21s gh/gasoonjia/181/head
gh/gasoonjia/181/head
34m 21s
Arm backend: Add IO copy tracking to perf_monitor (#22672) Test WebGPU Backend #14756: Commit dee51bb pushed by emmakujala
36m 59s main
main
36m 59s
[CUDA] Preserve fallback when remerging PTEs Test WebGPU Backend #14755: Pull request #22670 synchronize by Gasoonjia
34m 57s fix/cuda-remerge-fallback
fix/cuda-remerge-fallback
34m 57s
Arm backend: Align static KV-cache tests to extensions/llm (#22641) Test WebGPU Backend #14754: Commit a457114 pushed by tom-arm
36m 24s main
main
36m 24s
Qualcomm AI Engine Direct - [LLM QAT] Embedding + LM head W4 PCQ supp… Test WebGPU Backend #14753: Commit 176fd9d pushed by psiddh
39m 1s main
main
39m 1s
[ET-VK] Synthesize the layer_norm affine parameters that are absent Test WebGPU Backend #14752: Pull request #22506 synchronize by msluszniak
Action required msluszniak:ms/vulkan-layer-norm-optional-affine
msluszniak:ms/vulkan-layer-norm-optional-affine
Action required
NXP backend: Add QAT support to Neutron lowering recipes. (#22642) Test WebGPU Backend #14751: Commit 095bf6b pushed by MartinPavella
37m 4s main
main
37m 4s
[ET-VK] Wire the missing resize functions for embedding and index_select Test WebGPU Backend #14750: Pull request #22410 synchronize by msluszniak
Action required msluszniak:ms/vulkan-embedding-index-select-resize
msluszniak:ms/vulkan-embedding-index-select-resize
Action required
Move trunk.yml, periodic.yml and nightly.yml to linux_job_v3 Test WebGPU Backend #14749: Pull request #22248 synchronize by huydhn
34m 37s osdc/v3-trunk
osdc/v3-trunk
34m 37s
Arm backend: Document Model Explorer performance overlays Test WebGPU Backend #14748: Pull request #22675 opened by perheld
38m 35s perheld:change-1332361
perheld:change-1332361
38m 35s
Arm backend: Delegate constant tensor index Test WebGPU Backend #14747: Pull request #22674 opened by perheld
35m 27s perheld:change-1321554
perheld:change-1321554
35m 27s
Bump js-yaml from 3.15.0 to 3.15.2 in /extension/wasm/test Test WebGPU Backend #14746: Pull request #22673 opened by dependabot Bot
36m 35s dependabot/npm_and_yarn/extension/wasm/test/js-yaml-3.15.2
dependabot/npm_and_yarn/extension/wasm/test/js-yaml-3.15.2
36m 35s
[Reland] Move pull.yml to linux_job_v3 (#22632) Test WebGPU Backend #14745: Commit d3a225e pushed by huydhn
38m 35s main
main
38m 35s
[ET-VK] Serialize non-finite floats using flatc's spelling Test WebGPU Backend #14744: Pull request #22307 synchronize by msluszniak
Action required msluszniak:ms/vulkan-serialize-nonfinite-floats
msluszniak:ms/vulkan-serialize-nonfinite-floats
Action required
[ET-VK] Scale softmax workers with the row length and reduce as a tree Test WebGPU Backend #14743: Pull request #22349 synchronize by msluszniak
Action required msluszniak:ms/vulkan-softmax-scale-workers
msluszniak:ms/vulkan-softmax-scale-workers
Action required