Test Vulkan Backend (specialized runners)

Actions

All workflows
Workflows
- cuda-perf cuda-perf
- Promote commit to viable/strict Promote commit to viable/strict
- pull pull
- trunk trunk
- Update viable/strict Update viable/strict
- Test Vulkan Backend (specialized runners) Test Vulkan Backend (specialized runners)
- .github/workflows/_link_check.yml .github/workflows/_link_check.yml
- Add Open External Contributor PRs and Issues to PyTorch Org Project 136 Add Open External Contributor PRs and Issues to PyTorch Org Project 136
- Android Android
- Android Release Artifacts Android Release Artifacts
- Android Release on Tag Android Release on Tag
Management
- Caches
- Deployments

Test Vulkan Backend (specialized runners)

Actions

Loading...
Loading

600 workflow runs

[ExecuTorch][Vulkan] Add et_vk.linear_dW kernel (dense fp32 weight-grad GEMM) Test Vulkan Backend (specialized runners) #506: Pull request #21093 opened by pytorchbot

17m 58s gh/JCNTH/78/orig

gh/JCNTH/78/orig

17m 58s

[ExecuTorch][Vulkan] Tests for et_vk.adamw_step Test Vulkan Backend (specialized runners) #505: Pull request #21092 opened by pytorchbot

19m 25s gh/JCNTH/77/orig

gh/JCNTH/77/orig

19m 25s

[ExecuTorch][Vulkan] Tests for et_vk.adamw_step Test Vulkan Backend (specialized runners) #504: Pull request #21091 opened by pytorchbot

19m 29s gh/JCNTH/77/orig

gh/JCNTH/77/orig

19m 29s

[ExecuTorch][Vulkan] Add et_vk.adamw_step kernel (on-GPU AdamW optimizer step) Test Vulkan Backend (specialized runners) #503: Pull request #21090 opened by pytorchbot

19m 51s gh/JCNTH/76/orig

gh/JCNTH/76/orig

19m 51s

[ExecuTorch][WebGPU] Add et_vk.adamw_step (on-GPU AdamW optimizer step) to the WebGPU backend Test Vulkan Backend (specialized runners) #502: Pull request #21088 opened by pytorchbot

21m 2s gh/JCNTH/74/orig

gh/JCNTH/74/orig

21m 2s

[ExecuTorch][WebGPU] Add et_vk.fused_ce (fused cross-entropy) to the WebGPU backend Test Vulkan Backend (specialized runners) #501: Pull request #21086 opened by pytorchbot

22m 13s gh/JCNTH/72/orig

gh/JCNTH/72/orig

22m 13s

[ExecuTorch][WebGPU] Add q4gsw training kernels (backward, weight-grad, requant) to the WebGPU backend Test Vulkan Backend (specialized runners) #500: Pull request #21084 opened by pytorchbot

22m 59s gh/JCNTH/70/orig

gh/JCNTH/70/orig

22m 59s

[ExecuTorch][WebGPU] Add select/boolean ops (where, scalar compares, logical_not) to the WebGPU backend Test Vulkan Backend (specialized runners) #499: Pull request #21078 opened by pytorchbot

26m 46s gh/JCNTH/64/orig

gh/JCNTH/64/orig

26m 46s

Add cooperative matrix dispatch for quantized linear Test Vulkan Backend (specialized runners) #498: Pull request #21069 opened by SS-JIA

43m 48s SS-JIA:export-D110336871

SS-JIA:export-D110336871

43m 48s

Bump PyTorch pin to 2.13 (#20967) Test Vulkan Backend (specialized runners) #497: Commit 294c328 pushed by JacobSzwejbka

1m 54s main

main

1m 54s

[ET-VK] Add cooperative matrix dispatch for quantized linear Test Vulkan Backend (specialized runners) #496: Pull request #19892 synchronize by SS-JIA

41m 12s sarc-acl:yanwen/quant-dev

sarc-acl:yanwen/quant-dev

41m 12s

Fix portable pybindings COW ABI dependency (#21019) Test Vulkan Backend (specialized runners) #495: Commit 5442036 pushed by JakeStevens

47m 19s main

main

47m 19s

[ET-VK] Add cooperative matrix dispatch for quantized linear Test Vulkan Backend (specialized runners) #494: Pull request #19892 synchronize by SS-JIA

8m 7s sarc-acl:yanwen/quant-dev

sarc-acl:yanwen/quant-dev

8m 7s

migrate 3 fbcode-only TARGETS dirs with placeholder BUCK siblings (#21066) Test Vulkan Backend (specialized runners) #493: Pull request #21066 opened by bigfootjon

40m 56s bigfootjon:export-D109082045

bigfootjon:export-D109082045

40m 56s

[ET-VK][sdpa] Vendor-adaptive head_dim output-tiling (TILE_N4=2) in GQA AV coop-GEMV Test Vulkan Backend (specialized runners) #492: Pull request #21064 opened by SS-JIA

41m 21s gh/SS-JIA/577/head

gh/SS-JIA/577/head

41m 21s

[ET-VK][sdpa] Reuse shared V cache across GQA query heads in AV coop-GEMV Test Vulkan Backend (specialized runners) #491: Pull request #21063 opened by SS-JIA

42m 41s gh/SS-JIA/576/head

gh/SS-JIA/576/head

42m 41s

[ET-VK][sdpa] Add SDPA operator perf benchmark binary (test_sdpa) Test Vulkan Backend (specialized runners) #490: Pull request #21062 opened by SS-JIA

42m 38s gh/SS-JIA/575/head

gh/SS-JIA/575/head

42m 38s

Arm backend: Rerun duplicate-user fusion after TOSA lowering (#21041) Test Vulkan Backend (specialized runners) #489: Commit 667c91b pushed by YufengShi-dudu

38s main

main

38s

Arm backend: Add tests for automatic list of supported ops (#21053) Test Vulkan Backend (specialized runners) #488: Commit 2c92642 pushed by wwwind

40s main

main

40s

Arm backend: Handle grid_sample qparams in shader (#20963) Test Vulkan Backend (specialized runners) #487: Commit 69a9918 pushed by robell

38s main

main

38s

[ExecuTorch][Vulkan] Tests for et_vk.linear_q4gsw_backward Test Vulkan Backend (specialized runners) #486: Pull request #20944 synchronize by JCNTH

47m 9s gh/JCNTH/83/head

gh/JCNTH/83/head

47m 9s

[ExecuTorch][Vulkan] Add et_vk.q4gsw_requant kernel (STE re-quant to W_4X8) Test Vulkan Backend (specialized runners) #485: Pull request #20945 synchronize by JCNTH

47m 30s gh/JCNTH/84/head

gh/JCNTH/84/head

47m 30s

[ExecuTorch][Vulkan] Tests for et_vk.q4gsw_requant Test Vulkan Backend (specialized runners) #484: Pull request #20946 synchronize by JCNTH

47m 25s gh/JCNTH/85/head

gh/JCNTH/85/head

47m 25s

[ExecuTorch][Vulkan] Tests for et_vk.fused_ce Test Vulkan Backend (specialized runners) #483: Pull request #20942 synchronize by JCNTH

47m 19s gh/JCNTH/81/head

gh/JCNTH/81/head

47m 19s

[ExecuTorch][Vulkan] Add et_vk.linear_q4gsw_backward kernel (4-bit input-grad) Test Vulkan Backend (specialized runners) #482: Pull request #20943 synchronize by JCNTH

47m 21s gh/JCNTH/82/head

gh/JCNTH/82/head

47m 21s

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Actions

Workflows

Management