Add hardware check to fp8 quant #1314
Merged
Conversation
This file contains 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1314
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 9624574 with merge base 8b1b168 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jainapurva
force-pushed
the
fp8_check
branch
from
90b6c38 to
88b6ba1
Compare
jerryzh168
reviewed
Nov 19, 2024
drisspg
reviewed
Nov 19, 2024
torchao/quantization/quant_api.py
Outdated
| @@ -939,6 +940,9 @@ def float8_dynamic_activation_float8_weight( | |||
| mm_config (Float8MMConfig): Configuration for the matrix multiplication. Default uses fast accumulation. | |||
|
|
|||
| """ | |||
| assert ( | |||
| is_cuda_8_9 | |||
| ), "Float8 dynamic activation quantization is only supported on CUDA 8.9 and above" | |||
There was a problem hiding this comment.
This should also be supported on AMD. We should probably update this check.
cc @jeffdaily
Summary: Test Plan: Tested on AMD Instinct MI300X Reviewers: Subscribers: Tasks: Tags:
jainapurva
force-pushed
the
fp8_check
branch
from
04e3529 to
2423c1d
Compare
drisspg
approved these changes
Nov 22, 2024
drisspg
reviewed
Nov 22, 2024
torchao/quantization/quant_api.py
Outdated
| @@ -939,6 +941,9 @@ def float8_dynamic_activation_float8_weight( | |||
| mm_config (Float8MMConfig): Configuration for the matrix multiplication. Default uses fast accumulation. | |||
|
|
|||
| """ | |||
| assert ( | |||
| is_cuda_8_9 or is_MI300() | |||
There was a problem hiding this comment.
if granularity is PerTensor then it is sm89 if it is PerRow then it is currenlty sm90 or higher
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Add hardware check to ensure fp8 quantization only attempts runs on compatible hardware.
Test Plan: Ran float8_dynamic_quant on A100, MI300X, H100
Issue: #1188