Skip to content

Actions: pytorch/executorch

Actions

Test Vulkan Backend (specialized runners)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
vulkan.yml
604 workflow runs
604 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
rename TARGETS-only fbcode dirs with rules to BUCK (xplat-safe) (#20793) Test Vulkan Backend (specialized runners) #435: Commit d28ef1c pushed by meta-codesync Bot
53s main
main
53s
[ExecuTorch][Vulkan] Add et_vk.adamw_step kernel (on-GPU AdamW optimizer step) Test Vulkan Backend (specialized runners) #434: Pull request #20937 synchronize by JCNTH
39m 50s gh/JCNTH/76/head
gh/JCNTH/76/head
39m 50s
[ExecuTorch][WebGPU] Add q4gsw training kernels (backward, weight-grad, requant) to the WebGPU backend Test Vulkan Backend (specialized runners) #433: Pull request #20931 synchronize by JCNTH
39m 51s gh/JCNTH/70/head
gh/JCNTH/70/head
39m 51s
[ExecuTorch][Vulkan] Add et_vk.fused_ce kernels (fused cross-entropy loss + dlogits) Test Vulkan Backend (specialized runners) #432: Pull request #20941 synchronize by JCNTH
39m 29s gh/JCNTH/80/head
gh/JCNTH/80/head
39m 29s
[ExecuTorch][Vulkan] Tests for et_vk.linear_q4gsw_backward Test Vulkan Backend (specialized runners) #431: Pull request #20944 synchronize by JCNTH
39m 29s gh/JCNTH/83/head
gh/JCNTH/83/head
39m 29s
[ExecuTorch][Vulkan] Add et_vk.linear_q4gsw_backward kernel (4-bit input-grad) Test Vulkan Backend (specialized runners) #430: Pull request #20943 synchronize by JCNTH
39m 32s gh/JCNTH/82/head
gh/JCNTH/82/head
39m 32s
[ExecuTorch][Vulkan] Tests for et_vk.linear_dW Test Vulkan Backend (specialized runners) #429: Pull request #20940 synchronize by JCNTH
39m 59s gh/JCNTH/79/head
gh/JCNTH/79/head
39m 59s
[ExecuTorch][Vulkan] Tests for et_vk.adamw_step Test Vulkan Backend (specialized runners) #428: Pull request #20938 synchronize by JCNTH
39m 31s gh/JCNTH/77/head
gh/JCNTH/77/head
39m 31s
[ExecuTorch][Vulkan] Add et_vk.linear_dW kernel (dense fp32 weight-grad GEMM) Test Vulkan Backend (specialized runners) #427: Pull request #20939 synchronize by JCNTH
39m 30s gh/JCNTH/78/head
gh/JCNTH/78/head
39m 30s
[ExecuTorch][Vulkan] Tests for et_vk.q4gsw_requant Test Vulkan Backend (specialized runners) #426: Pull request #20946 synchronize by JCNTH
39m 34s gh/JCNTH/85/head
gh/JCNTH/85/head
39m 34s
[ExecuTorch][Vulkan] Add et_vk.q4gsw_requant kernel (STE re-quant to W_4X8) Test Vulkan Backend (specialized runners) #425: Pull request #20945 synchronize by JCNTH
39m 33s gh/JCNTH/84/head
gh/JCNTH/84/head
39m 33s
[ExecuTorch][WebGPU] Add et_vk.fused_ce (fused cross-entropy) to the WebGPU backend Test Vulkan Backend (specialized runners) #424: Pull request #20933 synchronize by JCNTH
39m 54s gh/JCNTH/72/head
gh/JCNTH/72/head
39m 54s
[ExecuTorch][Vulkan] Tests for et_vk.fused_ce Test Vulkan Backend (specialized runners) #423: Pull request #20942 synchronize by JCNTH
39m 36s gh/JCNTH/81/head
gh/JCNTH/81/head
39m 36s
[ExecuTorch][WebGPU] Add et_vk.adamw_step (on-GPU AdamW optimizer step) to the WebGPU backend Test Vulkan Backend (specialized runners) #422: Pull request #20935 synchronize by JCNTH
39m 53s gh/JCNTH/74/head
gh/JCNTH/74/head
39m 53s
AI: [G3] dequantize_per_tensor asym SIMD: integer zero-point subtract… Test Vulkan Backend (specialized runners) #421: Commit 2c90c5e pushed by zonglinpeng
2m 12s main
main
2m 12s
[ExecuTorch][Vulkan] Tests for et_vk.linear_q4gsw_backward Test Vulkan Backend (specialized runners) #419: Pull request #20944 synchronize by JCNTH
25m 52s gh/JCNTH/83/head
gh/JCNTH/83/head
25m 52s
[ExecuTorch][Vulkan] Tests for et_vk.linear_dW Test Vulkan Backend (specialized runners) #420: Pull request #20940 synchronize by JCNTH
25m 46s gh/JCNTH/79/head
gh/JCNTH/79/head
25m 46s
[ExecuTorch][WebGPU] Add et_vk.fused_ce (fused cross-entropy) to the WebGPU backend Test Vulkan Backend (specialized runners) #418: Pull request #20933 synchronize by JCNTH
25m 31s gh/JCNTH/72/head
gh/JCNTH/72/head
25m 31s
[ExecuTorch][Vulkan] Tests for et_vk.q4gsw_requant Test Vulkan Backend (specialized runners) #417: Pull request #20946 synchronize by JCNTH
25m 27s gh/JCNTH/85/head
gh/JCNTH/85/head
25m 27s
[ExecuTorch][Vulkan] Add et_vk.fused_ce kernels (fused cross-entropy loss + dlogits) Test Vulkan Backend (specialized runners) #416: Pull request #20941 synchronize by JCNTH
25m 57s gh/JCNTH/80/head
gh/JCNTH/80/head
25m 57s
[ExecuTorch][Vulkan] Add et_vk.linear_q4gsw_backward kernel (4-bit input-grad) Test Vulkan Backend (specialized runners) #415: Pull request #20943 synchronize by JCNTH
25m 50s gh/JCNTH/82/head
gh/JCNTH/82/head
25m 50s
[ExecuTorch][Vulkan] Tests for et_vk.fused_ce Test Vulkan Backend (specialized runners) #414: Pull request #20942 synchronize by JCNTH
25m 26s gh/JCNTH/81/head
gh/JCNTH/81/head
25m 26s
[ExecuTorch][Vulkan] Add et_vk.q4gsw_requant kernel (STE re-quant to W_4X8) Test Vulkan Backend (specialized runners) #413: Pull request #20945 synchronize by JCNTH
25m 38s gh/JCNTH/84/head
gh/JCNTH/84/head
25m 38s
[ExecuTorch][Vulkan] Add et_vk.adamw_step kernel (on-GPU AdamW optimizer step) Test Vulkan Backend (specialized runners) #412: Pull request #20937 synchronize by JCNTH
25m 47s gh/JCNTH/76/head
gh/JCNTH/76/head
25m 47s
[ExecuTorch][WebGPU] Add et_vk.adamw_step (on-GPU AdamW optimizer step) to the WebGPU backend Test Vulkan Backend (specialized runners) #411: Pull request #20935 synchronize by JCNTH
25m 24s gh/JCNTH/74/head
gh/JCNTH/74/head
25m 24s