Skip to content

Actions: pytorch/executorch

Actions

Test Vulkan Backend (specialized runners)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
vulkan.yml
607 workflow runs
607 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
Remove unused using-declarations Test Vulkan Backend (specialized runners) #313: Pull request #20953 opened by cyyever
38m 44s cyyever:remove-unused-using
cyyever:remove-unused-using
38m 44s
Buck fwd-fix: wire up VGF Neural Statistics files (#20952) Test Vulkan Backend (specialized runners) #312: Commit 430ae39 pushed by psiddh
35s main
main
35s
[ET-VK][fix] Widen WAR barrier to a full memory dependency for reused tensors Test Vulkan Backend (specialized runners) #311: Pull request #20951 opened by pytorchbot
38m 45s gh/SS-JIA/572/orig
gh/SS-JIA/572/orig
38m 45s
[ExecuTorch][Vulkan] Add et_vk.q4gsw_requant kernel (STE re-quant to W_4X8) Test Vulkan Backend (specialized runners) #310: Pull request #20945 synchronize by JCNTH
24m 11s gh/JCNTH/84/head
gh/JCNTH/84/head
24m 11s
[ExecuTorch][WebGPU] Add et_vk.adamw_step (on-GPU AdamW optimizer step) to the WebGPU backend Test Vulkan Backend (specialized runners) #309: Pull request #20935 synchronize by JCNTH
37m 53s gh/JCNTH/74/head
gh/JCNTH/74/head
37m 53s
[ExecuTorch][Vulkan] Tests for et_vk.q4gsw_requant Test Vulkan Backend (specialized runners) #308: Pull request #20946 synchronize by JCNTH
24m 1s gh/JCNTH/85/head
gh/JCNTH/85/head
24m 1s
[ExecuTorch][WebGPU] Add select/boolean ops (where, scalar compares, logical_not) to the WebGPU backend Test Vulkan Backend (specialized runners) #307: Pull request #20925 synchronize by JCNTH
38m 2s gh/JCNTH/64/head
gh/JCNTH/64/head
38m 2s
[ExecuTorch][Vulkan] Add et_vk.linear_q4gsw_backward kernel (4-bit input-grad) Test Vulkan Backend (specialized runners) #306: Pull request #20943 synchronize by JCNTH
23m 47s gh/JCNTH/82/head
gh/JCNTH/82/head
23m 47s
[ExecuTorch][Vulkan] Add et_vk.adamw_step kernel (on-GPU AdamW optimizer step) Test Vulkan Backend (specialized runners) #305: Pull request #20937 synchronize by JCNTH
38m 6s gh/JCNTH/76/head
gh/JCNTH/76/head
38m 6s
[ExecuTorch][Vulkan] Tests for et_vk.adamw_step Test Vulkan Backend (specialized runners) #304: Pull request #20938 synchronize by JCNTH
37m 34s gh/JCNTH/77/head
gh/JCNTH/77/head
37m 34s
[ExecuTorch][Vulkan] Tests for et_vk.linear_dW Test Vulkan Backend (specialized runners) #303: Pull request #20940 synchronize by JCNTH
38m 27s gh/JCNTH/79/head
gh/JCNTH/79/head
38m 27s
[ExecuTorch][WebGPU] Add et_vk.fused_ce (fused cross-entropy) to the WebGPU backend Test Vulkan Backend (specialized runners) #302: Pull request #20933 synchronize by JCNTH
37m 53s gh/JCNTH/72/head
gh/JCNTH/72/head
37m 53s
[ExecuTorch][Vulkan] Tests for et_vk.fused_ce Test Vulkan Backend (specialized runners) #301: Pull request #20942 synchronize by JCNTH
23m 57s gh/JCNTH/81/head
gh/JCNTH/81/head
23m 57s
[ExecuTorch][Vulkan] Tests for et_vk.linear_q4gsw_backward Test Vulkan Backend (specialized runners) #300: Pull request #20944 synchronize by JCNTH
24m 20s gh/JCNTH/83/head
gh/JCNTH/83/head
24m 20s
[ExecuTorch][WebGPU] Add q4gsw training kernels (backward, weight-grad, requant) to the WebGPU backend Test Vulkan Backend (specialized runners) #299: Pull request #20931 synchronize by JCNTH
38m 27s gh/JCNTH/70/head
gh/JCNTH/70/head
38m 27s
[ExecuTorch][Vulkan] Add et_vk.linear_dW kernel (dense fp32 weight-grad GEMM) Test Vulkan Backend (specialized runners) #298: Pull request #20939 synchronize by JCNTH
37m 36s gh/JCNTH/78/head
gh/JCNTH/78/head
37m 36s
[ExecuTorch][Vulkan] Add et_vk.fused_ce kernels (fused cross-entropy loss + dlogits) Test Vulkan Backend (specialized runners) #297: Pull request #20941 synchronize by JCNTH
22m 48s gh/JCNTH/80/head
gh/JCNTH/80/head
22m 48s
[ET][Windows] Relax -Werror for ExecuTorch CPU kernels on the Windows host Test Vulkan Backend (specialized runners) #296: Pull request #20949 opened by SS-JIA
1h 1m 13s gh/SS-JIA/574/head
gh/SS-JIA/574/head
1h 1m 13s
[ET][Windows] Fix ExecuTorch Windows host build portability defects Test Vulkan Backend (specialized runners) #295: Pull request #20948 opened by SS-JIA
1h 1m 24s gh/SS-JIA/573/head
gh/SS-JIA/573/head
1h 1m 24s
[ExecuTorch][Vulkan] Tests for et_vk.linear_q4gsw_backward Test Vulkan Backend (specialized runners) #294: Pull request #20944 synchronize by JCNTH
24m 30s gh/JCNTH/83/head
gh/JCNTH/83/head
24m 30s
[ExecuTorch][WebGPU] Add et_vk.adamw_step (on-GPU AdamW optimizer step) to the WebGPU backend Test Vulkan Backend (specialized runners) #293: Pull request #20935 synchronize by JCNTH
44m 58s gh/JCNTH/74/head
gh/JCNTH/74/head
44m 58s
[ExecuTorch][Vulkan] Tests for et_vk.fused_ce Test Vulkan Backend (specialized runners) #292: Pull request #20942 synchronize by JCNTH
23m 2s gh/JCNTH/81/head
gh/JCNTH/81/head
23m 2s
[ExecuTorch][Vulkan] Add et_vk.fused_ce kernels (fused cross-entropy loss + dlogits) Test Vulkan Backend (specialized runners) #291: Pull request #20941 synchronize by JCNTH
23m 54s gh/JCNTH/80/head
gh/JCNTH/80/head
23m 54s
[ExecuTorch][Vulkan] Add et_vk.linear_q4gsw_backward kernel (4-bit input-grad) Test Vulkan Backend (specialized runners) #290: Pull request #20943 synchronize by JCNTH
24m 9s gh/JCNTH/82/head
gh/JCNTH/82/head
24m 9s
[ExecuTorch][WebGPU] Add et_vk.fused_ce (fused cross-entropy) to the WebGPU backend Test Vulkan Backend (specialized runners) #289: Pull request #20933 synchronize by JCNTH
45m 4s gh/JCNTH/72/head
gh/JCNTH/72/head
45m 4s
ProTip! You can narrow down the results and go further in time using created:<2026-07-14 or the other filters available.