script to run mlperf llama2 70b on gpu #1373
Open
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
jwyang-google
requested review from
gobbleturk,
khatwanimohit,
bvandermoon,
vipannalla,
RissyRan,
richjames0,
rni418,
gagika,
shralex,
yangyuwei,
SurbhiJainUSC,
hengtaoguo and
A9isha
as code owners
tohaowu
approved these changes
Mar 11, 2025
jwyang-google
force-pushed
the
gpu_mlperf_llama2
branch
from
ade7120 to
ffb234e
Compare
jwyang-google
force-pushed
the
gpu_mlperf_llama2
branch
from
ffb234e to
c0d68ba
Compare
bvandermoon
reviewed
Mar 11, 2025
Comment on lines
+1232
to
+1263
| if base_engine.model.quant: | ||
| engine.model.quant.quant_mode = base_engine.model.quant.quant_mode |
There was a problem hiding this comment.
Why is this piece needed?
There was a problem hiding this comment.
if the quantization is not enabled, we will have quant=None which raises error
There was a problem hiding this comment.
Got it, thanks. It won't cause issues that it's no longer set in other cases, right?
bvandermoon
reviewed
Mar 12, 2025
Comment on lines
+1232
to
+1263
| if base_engine.model.quant: | ||
| engine.model.quant.quant_mode = base_engine.model.quant.quant_mode |
There was a problem hiding this comment.
Got it, thanks. It won't cause issues that it's no longer set in other cases, right?
| fi | ||
|
|
||
| if [[ -z ${CHECKPOINT} ]] ; then | ||
| export CHECKPOINT="gs://jwyang/maxtext/direct_generate_param_only_checkpoint_llama2_70b_chat/checkpoints/0/items" |
There was a problem hiding this comment.
Can this bucket be an input argument instead? Or can we at least use a general bucket instead of a personal one?
There was a problem hiding this comment.
just changed it to a general bucket the inference team is using
jwyang-google
force-pushed
the
gpu_mlperf_llama2
branch
from
c0d68ba to
78d5c79
Compare
bvandermoon
approved these changes
Mar 12, 2025
jwyang-google
force-pushed
the
gpu_mlperf_llama2
branch
from
78d5c79 to
05e9667
Compare
parambole
requested review from
mitalisi,
gpolovets1,
mailvijayasingh,
jrplatin,
patemotter and
Lumosis
as code owners
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.
Description
Start with a short description of what the PR does and how this is a change from
the past.
The rest of the description includes relevant details and context, examples:
If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456
Notice 1: Once all tests pass, the "pull ready" label will automatically be assigned.
This label is used for administrative purposes. Please do not add it manually.
Notice 2: For external contributions, our settings currently require an approval from a MaxText maintainer to trigger CI tests.
Tests
Please describe how you tested this change, and include any instructions and/or
commands to reproduce.
Checklist
Before submitting this PR, please make sure (put X in square brackets):