Skip to content

feat: AIU sim for FP8 (DL8/DL16) added to triton kernel#159

Merged
chichun-charlie-liu merged 13 commits intofoundation-model-stack:mainfrom
chichun-charlie-liu:triton_aiu_sim
Jul 10, 2025
Merged

feat: AIU sim for FP8 (DL8/DL16) added to triton kernel#159
chichun-charlie-liu merged 13 commits intofoundation-model-stack:mainfrom
chichun-charlie-liu:triton_aiu_sim

Conversation

@chichun-charlie-liu
Copy link
Copy Markdown
Collaborator

Description of the change

in addition to INT8 AIU simulation, now FP8 is added to the triton kernel. AIU FP8 is using "DL8" matmul accumulated in "DL16", slightly different from GPU's FP8 e4m3 accum in FP32 (GPU local accumulator only uses ~22bits mantissa).

Was the PR tested

  • I have added >=1 unit test(s) for every new method I have added (if that coverage is difficult, please briefly explain the reason)
  • I have ensured all unit tests pass

Checklist for passing CI/CD:

  • All commits are signed showing "Signed-off-by: Name <email@domain.com>" with git commit -signoff or equivalent
  • PR title and commit messages adhere to Conventional Commits
  • Contribution is formatted with tox -e fix
  • Contribution passes linting with tox -e lint
  • Contribution passes spellcheck with tox -e spellcheck
  • Contribution passes all unit tests with tox -e unit

Note: CI/CD performs unit tests on multiple versions of Python from a fresh install. There may be differences with your local environment and the test environment.

chichun-charlie-liu and others added 12 commits June 26, 2025 17:57
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Signed-off-by: cliu-us <cliu@us.ibm.com>
Comment thread fms_mo/custom_ext_kernels/triton_kernels.py Outdated
Comment thread fms_mo/modules/linear.py
Comment thread fms_mo/utils/dq_utils.py
Copy link
Copy Markdown
Collaborator

@BrandonGroth BrandonGroth left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will review again once set up as a PR

Signed-off-by: cliu-us <cliu@us.ibm.com>
@chichun-charlie-liu chichun-charlie-liu merged commit 0e98567 into foundation-model-stack:main Jul 10, 2025
11 checks passed
@chichun-charlie-liu chichun-charlie-liu deleted the triton_aiu_sim branch July 10, 2025 17:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants