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
2,992 workflow run results
2,992 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add benchmarking scripts
Run the aoti runner with CUDA using stories #2356: Pull request #1030 synchronize by Jack-Khuu
Add benchmarking scripts
Run the README instructions - with stories - on MPS/MacOS #1860: Pull request #1030 synchronize by Jack-Khuu
Add benchmarking scripts
Run the README instructions - with stories - on MacOS #1971: Pull request #1030 synchronize by Jack-Khuu
Add benchmarking scripts
Run the README instructions - with stories #1971: Pull request #1030 synchronize by Jack-Khuu
Add benchmarking scripts
Run parallel prefill #2246: Pull request #1030 synchronize by Jack-Khuu
recognize and issue error if GPU does not support bf16
Run the aoti runner with CUDA using stories #2355: Pull request #1344 synchronize by mikekgfb
recognize and issue error if GPU does not support bf16
Run the README instructions - with stories #1970: Pull request #1344 synchronize by mikekgfb
recognize and issue error if GPU does not support bf16
Run the README instructions - with stories - on MacOS #1970: Pull request #1344 synchronize by mikekgfb
recognize and issue error if GPU does not support bf16
Run the README instructions - with stories - on MPS/MacOS #1859: Pull request #1344 synchronize by mikekgfb
[AOTI] Remove the original model weights in Python deployment
Run the aoti runner with CUDA using stories #2354: Pull request #1337 synchronize by desertfire
[AOTI] Remove the original model weights in Python deployment
Run the README instructions - with stories #1969: Pull request #1337 synchronize by desertfire
16m 37s desertfire/1302
[AOTI] Remove the original model weights in Python deployment
Run the README instructions - with stories - on MPS/MacOS #1858: Pull request #1337 synchronize by desertfire
12m 17s desertfire/1302
[AOTI] Remove the original model weights in Python deployment
Run the README instructions - with stories - on MacOS #1969: Pull request #1337 synchronize by desertfire
Minor fixes to PT2 export path: enum typo and max_seq_len (#1343)
Run the README instructions - with stories #1968: Commit 54455a3 pushed by Jack-Khuu
17m 11s main
Minor fixes to PT2 export path: enum typo and max_seq_len (#1343)
Run the README instructions - with stories - on MacOS #1968: Commit 54455a3 pushed by Jack-Khuu
10m 35s main
Minor fixes to PT2 export path: enum typo and max_seq_len (#1343)
Run the README instructions - with stories - on MPS/MacOS #1857: Commit 54455a3 pushed by Jack-Khuu
10m 36s main
Minor fixes to PT2 export path: enum typo and max_seq_len (#1343)
Run the aoti runner with CUDA using stories #2353: Commit 54455a3 pushed by Jack-Khuu
10m 20s main
recognize and issue error if GPU does not support bf16
Run the aoti runner with CUDA using stories #2352: Pull request #1344 synchronize by mikekgfb