add ScaleToHwAligned for fp8 vllm model loading #118
Merged
Conversation
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
changwangss
requested review from
kzawora-intel,
madamczyk-intel,
michalkuligowski,
mgawarkiewicz,
tzielinski-habana and
afierka-intel
as code owners
michalkuligowski
requested changes
Mar 24, 2025
There was a problem hiding this comment.
vllm-fork CI fails with those changes, please check tests in HabanaAI/vllm-fork#941
dudilester
reviewed
Apr 1, 2025
Signed-off-by: changwangss <[email protected]>
Signed-off-by: changwangss <[email protected]>
changwangss
force-pushed
the
wangchang/hw_scale
branch
from
4d7a4fb to
8f26a9c
Compare
Signed-off-by: changwangss <[email protected]>
michalkuligowski
pushed a commit
to HabanaAI/vllm-fork
that referenced
this pull request
Apr 8, 2025
https://jira.habana-labs.com/browse/SW-207506 the scales provided by neuralmagic fp8 model method are maxabs, it need do hw scale align to adapt hpu platform to get better accuracy and performance. I add the class `ConvertScaleHwAlign` in vllm-hpu-extension(HabanaAI/vllm-hpu-extension#118) and call it in vllm-fork. the class also include the device check and make factor first if the device is G2. it is used for loading the models in this link. https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127 --------- Signed-off-by: changwangss <[email protected]>
imangohari1
pushed a commit
to imangohari1/vllm-fork
that referenced
this pull request
Apr 8, 2025
https://jira.habana-labs.com/browse/SW-207506 the scales provided by neuralmagic fp8 model method are maxabs, it need do hw scale align to adapt hpu platform to get better accuracy and performance. I add the class `ConvertScaleHwAlign` in vllm-hpu-extension(HabanaAI/vllm-hpu-extension#118) and call it in vllm-fork. the class also include the device check and make factor first if the device is G2. it is used for loading the models in this link. https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127 --------- Signed-off-by: changwangss <[email protected]>
tvoas
pushed a commit
to tvoas/vllm-fork
that referenced
this pull request
Apr 9, 2025
https://jira.habana-labs.com/browse/SW-207506 the scales provided by neuralmagic fp8 model method are maxabs, it need do hw scale align to adapt hpu platform to get better accuracy and performance. I add the class `ConvertScaleHwAlign` in vllm-hpu-extension(HabanaAI/vllm-hpu-extension#118) and call it in vllm-fork. the class also include the device check and make factor first if the device is G2. it is used for loading the models in this link. https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127 --------- Signed-off-by: changwangss <[email protected]>
bkowalskiINTEL
pushed a commit
to HabanaAI/vllm-fork
that referenced
this pull request
Apr 14, 2025
https://jira.habana-labs.com/browse/SW-207506 the scales provided by neuralmagic fp8 model method are maxabs, it need do hw scale align to adapt hpu platform to get better accuracy and performance. I add the class `ConvertScaleHwAlign` in vllm-hpu-extension(HabanaAI/vllm-hpu-extension#118) and call it in vllm-fork. the class also include the device check and make factor first if the device is G2. it is used for loading the models in this link. https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127 --------- Signed-off-by: changwangss <[email protected]>
michalkuligowski
added a commit
that referenced
this pull request
Apr 15, 2025
This reverts commit 145c63d.
Kacper-Pietkun
pushed a commit
that referenced
this pull request
Apr 15, 2025
* add ScaleToHwAligned for fp8 vllm model loading Signed-off-by: changwangss <[email protected]> * remove import Signed-off-by: changwangss <[email protected]> * improve structure Signed-off-by: changwangss <[email protected]> --------- Signed-off-by: changwangss <[email protected]>
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.
https://jira.habana-labs.com/browse/SW-207506