Skip to content

Actions: pytorch/ao

Actions

Run Float8 Tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
float8_test.yml
5,009 workflow runs
5,009 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add CUTLASS-based W4A4 Run Float8 Tests #5268: Pull request #1515 synchronize by gau-nernst
February 1, 2025 03:25 13m 39s gau-nernst:w4a4
gau-nernst:w4a4
February 1, 2025 03:25 13m 39s
Add CUTLASS-based W4A4 Run Float8 Tests #5267: Pull request #1515 synchronize by gau-nernst
February 1, 2025 02:53 12m 17s gau-nernst:w4a4
gau-nernst:w4a4
February 1, 2025 02:53 12m 17s
[Fix]: Fallback to KleidiAI channelwise kernel groupsize isnt suitable Run Float8 Tests #5266: Pull request #1647 opened by ng-05
January 31, 2025 16:15 Action required ng-05:kleidiai_fallback
ng-05:kleidiai_fallback
January 31, 2025 16:15 Action required
float8 rowwise training: add FSDP workaround (#1629) Run Float8 Tests #5265: Commit 3eb18e7 pushed by vkuzo
January 31, 2025 04:06 12m 0s main
main
January 31, 2025 04:06 12m 0s
[low-bit optim] Add coat for float8 optimizer Run Float8 Tests #5264: Pull request #1231 synchronize by MirMustafaAli
January 31, 2025 01:48 Action required MirMustafaAli:add_coat_optimizer
MirMustafaAli:add_coat_optimizer
January 31, 2025 01:48 Action required
Add boilerplate code Run Float8 Tests #5263: Pull request #1635 synchronize by jainapurva
January 30, 2025 22:56 11m 22s gh/jainapurva/3/head
gh/jainapurva/3/head
January 30, 2025 22:56 11m 22s
Update Run Float8 Tests #5262: Commit d42c725 pushed by jainapurva
January 30, 2025 22:56 11m 34s gh/jainapurva/3/head
gh/jainapurva/3/head
January 30, 2025 22:56 11m 34s
Ruff lint (#1646) Run Float8 Tests #5261: Commit 48fdd31 pushed by metascroy
January 30, 2025 21:21 12m 10s main
main
January 30, 2025 21:21 12m 10s
Ruff lint Run Float8 Tests #5260: Pull request #1646 opened by metascroy
January 30, 2025 19:18 11m 41s lint
lint
January 30, 2025 19:18 11m 41s
Change TORCH_LIBRARY to TORCH_LIBRARY_FRAGMENT Run Float8 Tests #5259: Pull request #1645 opened by metascroy
January 30, 2025 19:06 13m 9s torch-lib
torch-lib
January 30, 2025 19:06 13m 9s
[Feat]: Add support for kleidiai quantization schemes (#1447) Run Float8 Tests #5258: Commit 7815262 pushed by digantdesai
January 30, 2025 16:56 11m 54s main
main
January 30, 2025 16:56 11m 54s
[Feat]: Add support for kleidiai quantization schemes Run Float8 Tests #5256: Pull request #1447 synchronize by ng-05
January 30, 2025 16:19 Action required ng-05:kai_integration
ng-05:kai_integration
January 30, 2025 16:19 Action required
Tests jeanschmidt/NVIDIA_IMEX_CHANNELS changes Run Float8 Tests #5255: Pull request #1644 synchronize by jeanschmidt
January 30, 2025 16:17 1h 0m 19s jeanschmidt/NVIDIA_IMEX_CHANNELS
jeanschmidt/NVIDIA_IMEX_CHANNELS
January 30, 2025 16:17 1h 0m 19s
Tests jeanschmidt/NVIDIA_IMEX_CHANNELS changes Run Float8 Tests #5254: Pull request #1644 opened by jeanschmidt
January 30, 2025 16:10 33s jeanschmidt/NVIDIA_IMEX_CHANNELS
jeanschmidt/NVIDIA_IMEX_CHANNELS
January 30, 2025 16:10 33s
mx: add ceil and RNE rounding modes to the cast from fp32 to e8m0 Run Float8 Tests #5253: Pull request #1643 synchronize by vkuzo
January 30, 2025 04:54 11m 54s gh/vkuzo/23/head
gh/vkuzo/23/head
January 30, 2025 04:54 11m 54s
mx: add ceil and RNE rounding modes to the cast from fp32 to e8m0 Run Float8 Tests #5252: Commit 2301125 pushed by vkuzo
January 30, 2025 04:54 13m 53s gh/vkuzo/23/orig
gh/vkuzo/23/orig
January 30, 2025 04:54 13m 53s
Update Run Float8 Tests #5251: Commit 0d3d6f9 pushed by vkuzo
January 30, 2025 04:54 12m 7s gh/vkuzo/23/head
gh/vkuzo/23/head
January 30, 2025 04:54 12m 7s
Update Run Float8 Tests #5250: Commit 0d3d6f9 pushed by vkuzo
January 30, 2025 04:54 12m 2s gh/vkuzo/23/next
gh/vkuzo/23/next
January 30, 2025 04:54 12m 2s
mx: add ceil and RNE rounding modes to the cast from fp32 to e8m0 Run Float8 Tests #5249: Pull request #1643 synchronize by vkuzo
January 30, 2025 04:53 1m 20s gh/vkuzo/23/head
gh/vkuzo/23/head
January 30, 2025 04:53 1m 20s
mx: add ceil and RNE rounding modes to the cast from fp32 to e8m0 Run Float8 Tests #5248: Commit 8e058b7 pushed by vkuzo
January 30, 2025 04:53 1m 21s gh/vkuzo/23/orig
gh/vkuzo/23/orig
January 30, 2025 04:53 1m 21s
Update Run Float8 Tests #5247: Commit 85da297 pushed by vkuzo
January 30, 2025 04:53 1m 34s gh/vkuzo/23/next
gh/vkuzo/23/next
January 30, 2025 04:53 1m 34s
Update Run Float8 Tests #5246: Commit 85da297 pushed by vkuzo
January 30, 2025 04:53 1m 32s gh/vkuzo/23/head
gh/vkuzo/23/head
January 30, 2025 04:53 1m 32s
skip failing MX tests on cuda capability 10.0 (#1624) Run Float8 Tests #5245: Commit 463a872 pushed by vkuzo
January 30, 2025 04:44 11m 31s main
main
January 30, 2025 04:44 11m 31s
mx: add ceil and RNE rounding modes to the cast from fp32 to e8m0 Run Float8 Tests #5244: Commit adb32d7 pushed by vkuzo
January 30, 2025 04:32 11m 33s gh/vkuzo/23/orig
gh/vkuzo/23/orig
January 30, 2025 04:32 11m 33s
mx: add ceil and RNE rounding modes to the cast from fp32 to e8m0 Run Float8 Tests #5243: Pull request #1643 opened by vkuzo
January 30, 2025 04:32 11m 42s gh/vkuzo/23/head
gh/vkuzo/23/head
January 30, 2025 04:32 11m 42s