DeepSeek V3.1 announcement & Update benchmark tooling script#2817
Merged
copybara-service[bot] merged 1 commit intomainfrom Dec 16, 2025
Merged
DeepSeek V3.1 announcement & Update benchmark tooling script#2817copybara-service[bot] merged 1 commit intomainfrom
copybara-service[bot] merged 1 commit intomainfrom
Conversation
Rohan-Bierneni
requested review from
A9isha,
NuojCheng,
Obliviour,
RissyRan,
SujeethJinesh,
bvandermoon,
gagika,
gobbleturk,
jacoguzo,
jiangjy1982,
khatwanimohit,
mitalisi,
notabee,
richjames0,
shauryagup,
shralex and
vipannalla
as code owners
RissyRan
approved these changes
Dec 11, 2025
Collaborator
RissyRan
left a comment
RissyRan
left a comment
There was a problem hiding this comment.
Thanks! A few minor comments.
Rohan-Bierneni
force-pushed
the
rbierneni-mmlu
branch
from
4b2abc2 to
7f76b89
Compare
shuningjin
reviewed
Dec 11, 2025
shuningjin
approved these changes
Dec 12, 2025
Rohan-Bierneni
force-pushed
the
rbierneni-mmlu
branch
from
8d95dab to
cadb323
Compare
Updated Readme with Deepseek V3.1 news Update Deepseek Readme with V3.1 info Updated port forward script Clean up script Resolve comments Update with R1 model in deepseek readme update doc since fp8 is now supported
Rohan-Bierneni
force-pushed
the
rbierneni-mmlu
branch
from
cadb323 to
49793aa
Compare
Collaborator
Author
|
Manually adding pull_review tag since all tests have passed |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
DeepSeek V3.1 has been verified in maxtext and this pr is to update MaxText to make the announcement. The files that were updated in the homepage Readme and the DeepSeek Readme. The steps taken to verify the V3.1 checkpoint in MaxText and command run are documented here: b/450580441.
Also, when running MMLU benchmark for DeepSeek V3.1, there was a small bug in a script for Maxtext api_server, the tool used to run benchmarks efficiently. The issue is when running multi-host via xpk, the script port_forward_xpk.sh fails with the message "PODS: unbound variable". This pr has the fix with the right filtering method to find the correct pod when running the xpk workload.
If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/450580441
Tests
The steps taken to verify the V3.1 checkpoint in MaxText and command run are documented here.
Checklist
Before submitting this PR, please make sure (put X in square brackets):
gemini-reviewlabel.