docs(mxfp): clarify that TPU/CPU use native fp8 dot_general fallback#323
Open
lokic233 wants to merge 2 commits into
Open
docs(mxfp): clarify that TPU/CPU use native fp8 dot_general fallback#323lokic233 wants to merge 2 commits into
lokic233 wants to merge 2 commits into
Conversation
The existing comment ('Once scaled_matmul supports TPU, we will enable it')
could be misread as TPU being unsupported. In fact, when mxfp_dot_general
returns None on TPU/CPU, the caller already falls through to
dot_general._fast_dot_general — a correct, MXU-accelerated native fp8 path.
This rewords the comment to state the current behavior clearly: GPU uses
the fused scaled_matmul path; TPU/CPU use the native tiled fp8 fallback.
No behavior change — comment only.
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
The comment at
qwix/_src/core/mxfp_dot.pyL50-52 reads:This could be misread as MXFP being unsupported on TPU. In fact, when
mxfp_dot_generalreturnsNoneon TPU/CPU, the caller already falls through todot_general._fast_dot_general— a correct, MXU-accelerated native fp8 path that works today.This rewords the comment to state the current behavior clearly.
Details
jax.nn.scaled_matmulpath (natively on Blackwell via cuDNN, emulated on legacy).None→ caller uses native tiled fp8dot_generalfallback (correct + accelerated).