Support Mixtral quantization using INC #188
Closed
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
dudilester
force-pushed
the
dev/dlester/mixtral_main_1
branch
from
f710cc7
to
3e503d0
Compare
dudilester
requested review from
HolyFalafel,
MrGeva,
Tiefen-boop,
Yantom1,
BacharL,
nirda7 and
ulivne
Tiefen-boop
reviewed
Aug 19, 2024
# Conflicts: # vllm/hpu/ops.py # vllm/model_executor/layers/quantization/inc.py
# Conflicts: # vllm/hpu/ops.py
Tiefen-boop
force-pushed
the
dev/dlester/mixtral_main_1
branch
from
789cc54
to
be7f696
Compare
Tiefen-boop
force-pushed
the
dev/dlester/mixtral_main_1
branch
3 times, most recently
from
53cdd9b
to
5b515fa
Compare
Tiefen-boop
force-pushed
the
dev/dlester/mixtral_main_1
branch
from
5b515fa
to
1a5fd1d
Compare
Tiefen-boop
force-pushed
the
dev/dlester/mixtral_main_1
branch
5 times, most recently
from
0dc3495
to
4ea6b7c
Compare
Tiefen-boop
force-pushed
the
dev/dlester/mixtral_main_1
branch
from
4ea6b7c
to
e7106dc
Compare
szutenberg
requested changes
Sep 3, 2024
| @@ -13,9 +13,6 @@ | |||
| from vllm.model_executor.utils import set_weight_attrs | |||
There was a problem hiding this comment.
@kzawora-intel could you check if these changes are upstreamable?
# Conflicts: # vllm/hpu/ops.py
szutenberg
approved these changes
Sep 5, 2024
jkaniecki
requested changes
Sep 10, 2024
| @@ -16,6 +16,7 @@ | |||
|
|
|||
| import habana_frameworks.torch as htorch | |||
| import torch | |||
| from neural_compressor.torch.quantization import finalize_calibration | |||
There was a problem hiding this comment.
This brakes taking fp8 measurements with TP>1 - please revert changes made to this file
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Outdated suggestions cannot be applied.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.
No description provided.