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

Actions: pytorch/torchchat

Actions

Run the README instructions - with stories - on MPS/MacOS

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
221 workflow run results
221 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Also use default max_seq_length of 128 for ExecuTorch native runner
Run the README instructions - with stories - on MPS/MacOS #1414: Pull request #1186 opened by swolchok
Default max_seq_length to 128 for ExecuTorch export
Run the README instructions - with stories - on MPS/MacOS #1413: Pull request #1170 synchronize by swolchok
export.py: fix custom SDPA type conversion logic & re-enable for bfloat16
Run the README instructions - with stories - on MPS/MacOS #1412: Pull request #1171 synchronize by swolchok
Use default max_seq_length of 128 when loading ExecuTorch models
Run the README instructions - with stories - on MPS/MacOS #1411: Pull request #1184 opened by swolchok
Android artifact update (#1138)
Run the README instructions - with stories - on MPS/MacOS #1410: Commit 04ea309 pushed by kirklandsign
10m 39s main
enable llava on torchchat
Run the README instructions - with stories - on MPS/MacOS #1409: Pull request #1183 synchronize by Gasoonjia
10m 18s llava-e2e
enable llava on torchchat
Run the README instructions - with stories - on MPS/MacOS #1408: Pull request #1183 synchronize by Gasoonjia
10m 13s llava-e2e
enable llava on torchchat
Run the README instructions - with stories - on MPS/MacOS #1407: Pull request #1183 synchronize by Gasoonjia
10m 15s llava-e2e
enable llava on torchchat
Run the README instructions - with stories - on MPS/MacOS #1406: Pull request #1183 opened by Gasoonjia
13m 22s llava-e2e
Add torchao
Run the README instructions - with stories - on MPS/MacOS #1405: Pull request #1182 synchronize by metascroy
10m 18s add-torchao
Add torchao
Run the README instructions - with stories - on MPS/MacOS #1404: Pull request #1182 opened by metascroy
10m 48s add-torchao
Default max_seq_length to 128 for ExecuTorch export
Run the README instructions - with stories - on MPS/MacOS #1403: Pull request #1170 synchronize by swolchok
add ConvertToLinear, disable custom SDPA for bfloat16
Run the README instructions - with stories - on MPS/MacOS #1401: Pull request #1169 synchronize by swolchok
export.py: fix custom SDPA type conversion logic & re-enable for bfloat16
Run the README instructions - with stories - on MPS/MacOS #1402: Pull request #1171 synchronize by swolchok
parallelize ExecuTorch build
Run the README instructions - with stories - on MPS/MacOS #1400: Pull request #1168 synchronize by swolchok
Update ExecuTorch pin to pick up bfloat16 fixes
Run the README instructions - with stories - on MPS/MacOS #1399: Pull request #1181 opened by swolchok
[Distributed] Make decode in flight optional
Run the README instructions - with stories - on MPS/MacOS #1398: Pull request #1180 synchronize by kwen2501
8m 51s batch_decode
Android artifact update
Run the README instructions - with stories - on MPS/MacOS #1397: Pull request #1138 synchronize by Jack-Khuu
[Distributed] Add lanes to KV cache (#1174)
Run the README instructions - with stories - on MPS/MacOS #1396: Commit 2cf4016 pushed by kwen2501
10m 18s main
Android artifact update
Run the README instructions - with stories - on MPS/MacOS #1395: Pull request #1138 synchronize by kirklandsign
Android artifact update
Run the README instructions - with stories - on MPS/MacOS #1394: Pull request #1138 synchronize by kirklandsign
Android artifact update
Run the README instructions - with stories - on MPS/MacOS #1393: Pull request #1138 synchronize by kirklandsign
add ConvertToLinear, disable custom SDPA for bfloat16
Run the README instructions - with stories - on MPS/MacOS #1391: Pull request #1169 synchronize by swolchok
export.py: fix custom SDPA type conversion logic & re-enable for bfloat16
Run the README instructions - with stories - on MPS/MacOS #1390: Pull request #1171 synchronize by swolchok
Default max_seq_length to 128 for ExecuTorch export
Run the README instructions - with stories - on MPS/MacOS #1392: Pull request #1170 synchronize by swolchok