Skip to content

Actions: pytorch/torchchat

Actions

Run the aoti runner with CUDA using stories

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
runner-cuda-dtype.yml
2,095 workflow runs
2,095 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Distributed] Fix new token's shape (#1254) Run the aoti runner with CUDA using stories #2103: Commit 5952bd1 pushed by kwen2501
October 2, 2024 21:45 8m 47s main
main
October 2, 2024 21:45 8m 47s
[Distributed] Fix new token's shape Run the aoti runner with CUDA using stories #2102: Pull request #1254 synchronize by kwen2501
October 2, 2024 20:26 8m 26s new_token_shape
new_token_shape
October 2, 2024 20:26 8m 26s
[Distributed] create model on meta device (#1227) Run the aoti runner with CUDA using stories #2101: Commit 8fcb3ba pushed by kwen2501
October 2, 2024 20:23 8m 27s main
main
October 2, 2024 20:23 8m 27s
[Distributed] Fix new token's shape Run the aoti runner with CUDA using stories #2100: Pull request #1254 synchronize by kwen2501
October 2, 2024 20:23 9m 0s new_token_shape
new_token_shape
October 2, 2024 20:23 9m 0s
[Distributed] create model on meta device Run the aoti runner with CUDA using stories #2099: Pull request #1227 synchronize by kwen2501
October 2, 2024 19:33 9m 2s meta_init
meta_init
October 2, 2024 19:33 9m 2s
Update packaging in AOTI path Run the aoti runner with CUDA using stories #2098: Pull request #896 synchronize by angelayi
October 2, 2024 18:14 8m 30s angelayi/aoti_python
angelayi/aoti_python
October 2, 2024 18:14 8m 30s
Update packaging in AOTI path Run the aoti runner with CUDA using stories #2097: Pull request #896 synchronize by angelayi
October 2, 2024 16:37 8m 22s angelayi/aoti_python
angelayi/aoti_python
October 2, 2024 16:37 8m 22s
Safetensors Run the aoti runner with CUDA using stories #2096: Pull request #1255 opened by gabe-l-hart
October 2, 2024 15:29 8m 58s gabe-l-hart:Safetensors-1249
gabe-l-hart:Safetensors-1249
October 2, 2024 15:29 8m 58s
[Distributed] Implement universal batch_decode & decode_in_flight for… Run the aoti runner with CUDA using stories #2095: Commit 77bac00 pushed by lessw2020
October 2, 2024 00:40 9m 8s main
main
October 2, 2024 00:40 9m 8s
[Distributed] Fix new token's shape Run the aoti runner with CUDA using stories #2094: Pull request #1254 opened by kwen2501
October 2, 2024 00:27 8m 40s new_token_shape
new_token_shape
October 2, 2024 00:27 8m 40s
Absorb non-MM OpenAI dialog parsing into generic input parsing (#1248) Run the aoti runner with CUDA using stories #2093: Commit 58185b6 pushed by Jack-Khuu
October 2, 2024 00:19 9m 13s main
main
October 2, 2024 00:19 9m 13s
Update packaging in AOTI path Run the aoti runner with CUDA using stories #2092: Pull request #896 synchronize by angelayi
October 2, 2024 00:04 9m 9s angelayi/aoti_python
angelayi/aoti_python
October 2, 2024 00:04 9m 9s
Update packaging in AOTI path Run the aoti runner with CUDA using stories #2091: Pull request #896 synchronize by angelayi
October 1, 2024 22:13 8m 21s angelayi/aoti_python
angelayi/aoti_python
October 1, 2024 22:13 8m 21s
Absorb non-MM OpenAI dialog parsing into generic input parsing Run the aoti runner with CUDA using stories #2090: Pull request #1248 synchronize by Jack-Khuu
October 1, 2024 20:38 8m 49s reunify-request-generation
reunify-request-generation
October 1, 2024 20:38 8m 49s
Absorb non-MM OpenAI dialog parsing into generic input parsing Run the aoti runner with CUDA using stories #2089: Pull request #1248 synchronize by Jack-Khuu
October 1, 2024 19:44 15m 56s reunify-request-generation
reunify-request-generation
October 1, 2024 19:44 15m 56s
Fix non-MM multiturn: Use legacy formatting (#1247) Run the aoti runner with CUDA using stories #2088: Commit edaa15c pushed by Jack-Khuu
October 1, 2024 19:41 15m 54s main
main
October 1, 2024 19:41 15m 54s
Update quantization.md (#1246) Run the aoti runner with CUDA using stories #2087: Commit 3c0f180 pushed by metascroy
October 1, 2024 19:36 9m 32s main
main
October 1, 2024 19:36 9m 32s
[Distributed] Bump torch version Run the aoti runner with CUDA using stories #2086: Pull request #1225 synchronize by kwen2501
October 1, 2024 19:14 9m 40s pin_torch
pin_torch
October 1, 2024 19:14 9m 40s
Fix non-MM multiturn: Use legacy formatting Run the aoti runner with CUDA using stories #2085: Pull request #1247 synchronize by Jack-Khuu
October 1, 2024 18:38 10m 51s fix-non-mm-chat
fix-non-mm-chat
October 1, 2024 18:38 10m 51s
Fix non-MM multiturn: Use legacy formatting Run the aoti runner with CUDA using stories #2084: Pull request #1247 opened by Jack-Khuu
October 1, 2024 18:36 10m 10s fix-non-mm-chat
fix-non-mm-chat
October 1, 2024 18:36 10m 10s
Only show MPS Compile Warning if compile is attempted (#1245) Run the aoti runner with CUDA using stories #2083: Commit 24d00ea pushed by Jack-Khuu
October 1, 2024 18:30 13m 0s main
main
October 1, 2024 18:30 13m 0s
Update quantization.md Run the aoti runner with CUDA using stories #2082: Pull request #1246 opened by metascroy
October 1, 2024 17:21 9m 1s metascroy-patch-2
metascroy-patch-2
October 1, 2024 17:21 9m 1s
Only show MPS Compile Warning if compile is attempted Run the aoti runner with CUDA using stories #2081: Pull request #1245 opened by Jack-Khuu
October 1, 2024 02:43 8m 37s mps-compile-msg
mps-compile-msg
October 1, 2024 02:43 8m 37s
Add MPS Fallback to support Torchtune Multimodal MPS (#1241) Run the aoti runner with CUDA using stories #2080: Commit 8a580dd pushed by Jack-Khuu
October 1, 2024 02:31 8m 50s main
main
October 1, 2024 02:31 8m 50s
Update multimodal.md to remove MPS message Run the aoti runner with CUDA using stories #2079: Pull request #1243 opened by Jack-Khuu
October 1, 2024 01:28 8m 45s Jack-Khuu-patch-26
Jack-Khuu-patch-26
October 1, 2024 01:28 8m 45s