Unverified Commit 85a91997 authored by Kirthi Shankar Sivamani's avatar Kirthi Shankar Sivamani Committed by GitHub
Browse files

Generalize quantization APIs for FP8/FP4/.. recipes (#2256)



* Initial API change
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Change all imports and api
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* format
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fixes
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix typo
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix recipe tets
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix more tests
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix docs, tests, and make Jax change as well
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Change internal uses of fp8_autocast
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Address nits
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* rename file
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* CG function, and small test fixes
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Change instances of make_graphed_callables internally
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Fix distributed tests
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Review
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Review
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Fix test and add more docs
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Cleanup test imports and minimize internal file imports
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Make is_bf16_available public
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fixes
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix tests
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Better docs and better api
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* format
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

* Apply suggestions from code review
Signed-off-by: default avatarTim Moon <4406448+timmoon10@users.noreply.github.com>

* fix nvfp4 test
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: default avatarKirthi Shankar Sivamani <ksivamani@nvidia.com>
Signed-off-by: default avatarTim Moon <4406448+timmoon10@users.noreply.github.com>
Co-authored-by: default avatarTim Moon <4406448+timmoon10@users.noreply.github.com>
parent ca6fedcf
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment