Skip to content
This repository was archived by the owner on Sep 10, 2025. It is now read-only.

Actions: pytorch/torchchat

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
1,426 workflow run results
1,426 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Use default max_seq_length of 128 when loading ExecuTorch models Run the README instructions - with stories #1540: Pull request #1190 synchronize by swolchok
31m 12s gh/swolchok/11/head
gh/swolchok/11/head
31m 12s
Update ExecuTorch pin to pick up bfloat16 fixes Run the README instructions - with stories - on MPS/MacOS #1432: Pull request #1187 synchronize by swolchok
30m 56s gh/swolchok/8/head
gh/swolchok/8/head
30m 56s
Default max_seq_length to 128 for ExecuTorch export Run parallel prefill #1818: Pull request #1192 synchronize by swolchok
37m 15s gh/swolchok/13/head
gh/swolchok/13/head
37m 15s
Update ExecuTorch pin to pick up bfloat16 fixes Run parallel prefill #1819: Pull request #1187 synchronize by swolchok
36m 50s gh/swolchok/8/head
gh/swolchok/8/head
36m 50s
Update ExecuTorch pin to pick up bfloat16 fixes pull #2852: Pull request #1187 synchronize by swolchok
40m 52s gh/swolchok/8/head
gh/swolchok/8/head
40m 52s
export.py: fix custom SDPA type conversion logic & re-enable for bfloat16 pull #2853: Pull request #1193 synchronize by swolchok
41m 4s gh/swolchok/14/head
gh/swolchok/14/head
41m 4s
Use default max_seq_length of 128 when loading ExecuTorch models pull #2851: Pull request #1190 synchronize by swolchok
40m 56s gh/swolchok/11/head
gh/swolchok/11/head
40m 56s
Default max_seq_length to 128 for ExecuTorch export Run the README instructions - with stories - on MPS/MacOS #1433: Pull request #1192 synchronize by swolchok
31m 59s gh/swolchok/13/head
gh/swolchok/13/head
31m 59s
parallelize ExecuTorch build Run the README instructions - with stories #1537: Pull request #1188 synchronize by swolchok
29m 7s gh/swolchok/9/head
gh/swolchok/9/head
29m 7s
parallelize ExecuTorch build Run the README instructions - with stories - on MPS/MacOS #1427: Pull request #1188 synchronize by swolchok
25m 58s gh/swolchok/9/head
gh/swolchok/9/head
25m 58s
add ConvertToLinear, disable custom SDPA for bfloat16 Run the README instructions - with stories #1536: Pull request #1189 synchronize by swolchok
26m 22s gh/swolchok/10/head
gh/swolchok/10/head
26m 22s
parallelize ExecuTorch build Run the README instructions - with stories - on MPS/MacOS #1426: Pull request #1188 synchronize by swolchok
24m 44s gh/swolchok/9/head
gh/swolchok/9/head
24m 44s
Use default max_seq_length of 128 when loading ExecuTorch models Run the README instructions - with stories #1538: Pull request #1190 synchronize by swolchok
27m 5s gh/swolchok/11/head
gh/swolchok/11/head
27m 5s
Use default max_seq_length of 128 when loading ExecuTorch models Run the README instructions - with stories - on MPS/MacOS #1428: Pull request #1190 synchronize by swolchok
27m 5s gh/swolchok/11/head
gh/swolchok/11/head
27m 5s
export.py: fix custom SDPA type conversion logic & re-enable for bfloat16 Run the README instructions - with stories - on MPS/MacOS #1429: Pull request #1193 synchronize by swolchok
27m 6s gh/swolchok/14/head
gh/swolchok/14/head
27m 6s
export.py: fix custom SDPA type conversion logic & re-enable for bfloat16 Run the README instructions - with stories - on MPS/MacOS #1430: Pull request #1193 synchronize by swolchok
27m 51s gh/swolchok/14/head
gh/swolchok/14/head
27m 51s
parallelize ExecuTorch build Run the README instructions - with stories #1539: Pull request #1188 synchronize by swolchok
27m 59s gh/swolchok/9/head
gh/swolchok/9/head
27m 59s
Use default max_seq_length of 128 when loading ExecuTorch models Run the README instructions - with stories - on MPS/MacOS #1431: Pull request #1190 synchronize by swolchok
28m 24s gh/swolchok/11/head
gh/swolchok/11/head
28m 24s
parallelize ExecuTorch build Run the aoti runner with CUDA using stories #1922: Pull request #1188 synchronize by swolchok
14m 29s gh/swolchok/9/head
gh/swolchok/9/head
14m 29s
Use default max_seq_length of 128 when loading ExecuTorch models Run the aoti runner with CUDA using stories #1924: Pull request #1190 synchronize by swolchok
14m 41s gh/swolchok/11/head
gh/swolchok/11/head
14m 41s
parallelize ExecuTorch build Run the aoti runner with CUDA using stories #1923: Pull request #1188 synchronize by swolchok
14m 37s gh/swolchok/9/head
gh/swolchok/9/head
14m 37s
add ConvertToLinear, disable custom SDPA for bfloat16 Run the aoti runner with CUDA using stories #1921: Pull request #1189 synchronize by swolchok
14m 38s gh/swolchok/10/head
gh/swolchok/10/head
14m 38s
add ConvertToLinear, disable custom SDPA for bfloat16 Run the README instructions - with stories - on MPS/MacOS #1425: Pull request #1189 synchronize by swolchok
22m 1s gh/swolchok/10/head
gh/swolchok/10/head
22m 1s
Default max_seq_length to 128 for ExecuTorch export Run the README instructions - with stories #1544: Pull request #1192 synchronize by swolchok
32m 11s gh/swolchok/13/head
gh/swolchok/13/head
32m 11s
add ConvertToLinear, disable custom SDPA for bfloat16 Run parallel prefill #1811: Pull request #1189 synchronize by swolchok
33m 56s gh/swolchok/10/head
gh/swolchok/10/head
33m 56s