docs: add 405b disaggregated serving documentation #496
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
ishandhanani
requested review from
hutm,
biswapanda,
julienmancuso,
hhzhang16,
nnshah1,
tanmayv25,
piotrm-nvidia,
ptarasiewiczNV,
ryanolson,
grahamking,
paulhendricks,
tmonty12,
GuanLuo,
rmccorm4,
tedzhouhk,
alec-flowers,
kkranen,
sshchoi,
PeaBrane and
mohammedabdulwahhab
as code owners
tlipoca9
reviewed
Apr 3, 2025
nnshah1
reviewed
Apr 3, 2025
ishandhanani
changed the title
nnshah1
reviewed
Apr 3, 2025
nnshah1
reviewed
Apr 3, 2025
nnshah1
reviewed
Apr 3, 2025
nnshah1
approved these changes
Apr 3, 2025
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Outdated suggestions cannot be applied.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.
Separate out multinode docs into their own file and add docs on how to run disaggregated serving with 405B.
Note as per #304 (comment) - we are currently limited to models that can be deployed on a single node. This PR provides instructions for successfully deploying 405b FP8 on a single 8xH100 node.
We are working on multi-node model support