Skip to content

Actions: pytorch/executorch

Actions

Docathon Labels Sync

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docathon-sync-label.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
Enable buck-native x86 simulator test for QNN op tests Docathon Labels Sync #4439: Pull request #20494 synchronize by billmguo
41s
41s
Enable buck-native x86 simulator test for QNN op tests Docathon Labels Sync #4438: Pull request #20494 edited by meta-codesync Bot
43s
43s
Remove _use_edge_ops=True (#20516) Docathon Labels Sync #4437: Pull request #20516 edited by meta-codesync Bot
28s
28s
Remove _use_edge_ops=True (#20516) Docathon Labels Sync #4436: Pull request #20516 synchronize by JakeStevens
21s
21s
Inline per-tensor SIMD fast path in fusion_g3 op_dequantize (#20499) Docathon Labels Sync #4435: Pull request #20499 edited by zonglinpeng
19s
19s
Vulkan: support Linux/Windows desktop GPUs and opt-in wheel builds Docathon Labels Sync #4434: Pull request #20138 synchronize by Reubend
34s
34s
MLX: on-device token sampling with Gumbel-max Docathon Labels Sync #4433: Pull request #20454 synchronize by kiymetakdemir
32s
32s
Enable buck-native x86 simulator test for QNN op tests Docathon Labels Sync #4432: Pull request #20494 synchronize by billmguo
28s
28s
Enable buck-native x86 simulator test for QNN op tests Docathon Labels Sync #4431: Pull request #20494 edited by meta-codesync Bot
18s
18s
Use caller CUDA stream for D2H and H2D copies (#20498) Docathon Labels Sync #4430: Pull request #20498 synchronize by Conarnar
22s
22s
Use caller CUDA stream for D2H and H2D copies (#20498) Docathon Labels Sync #4429: Pull request #20498 edited by meta-codesync Bot
32s
32s
Point VGF tests at model-converter 0.9.0 Docathon Labels Sync #4428: Pull request #20520 edited by pytorch-bot Bot
51s
51s
Point VGF tests at model-converter 0.9.0 Docathon Labels Sync #4427: Pull request #20520 opened by rascani
33s
33s
NOT FOR LAND Docathon Labels Sync #4426: Pull request #20519 opened by Gasoonjia
7m 57s
7m 57s
gemma4_31b: add OpenAI serving entrypoint Docathon Labels Sync #4425: Pull request #20473 synchronize by mergennachin
26s
26s
[gemma4_31b][cuda] Export Gemma4-31B @128k on 5090 Docathon Labels Sync #4424: Pull request #20480 synchronize by Gasoonjia
22s
22s
Allow context-binary lowering to use edge dialect ops (#20518) Docathon Labels Sync #4423: Pull request #20518 edited by pytorch-bot Bot
27s
27s
Use caller CUDA stream for D2H and H2D copies (#20498) Docathon Labels Sync #4422: Pull request #20498 synchronize by Conarnar
20s
20s
Allow context-binary lowering to use edge dialect ops (#20518) Docathon Labels Sync #4421: Pull request #20518 edited by meta-codesync Bot
21s
21s
Allow context-binary lowering to use edge dialect ops (#20518) Docathon Labels Sync #4420: Pull request #20518 synchronize by JakeStevens
24s
24s
MLX: on-device token sampling with Gumbel-max Docathon Labels Sync #4419: Pull request #20454 synchronize by kiymetakdemir
20s
20s
Qualcomm: cap inf replacement value to fix 16a16w accuracy regression Docathon Labels Sync #4418: Pull request #20471 synchronize by psiddh
24s
24s
Allow context-binary lowering to use edge dialect ops (#20518) Docathon Labels Sync #4417: Pull request #20518 opened by JakeStevens
29s
29s
Qualcomm: cap inf replacement value to fix 16a16w accuracy regression Docathon Labels Sync #4416: Pull request #20471 synchronize by psiddh
27s
27s
[ExecuTorch][WebGPU] Register-tile the SDPA QK/AV kernels Docathon Labels Sync #4415: Pull request #20507 synchronize by ghost
27s
27s
ProTip! You can narrow down the results and go further in time using created:<2026-06-25 or the other filters available.