-
Notifications
You must be signed in to change notification settings - Fork 281
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Torch deepseek v2 #1621
Merged
Merged
Torch deepseek v2 #1621
Changes from 1 commit
Commits
Show all changes
32 commits
Select commit
Hold shift + click to select a range
7bac22d
first
grimoire 77034bf
all model down
grimoire d7138f1
remove device mesh
grimoire fd3f84f
fix triton==2.2.0
1cf9990
WIP
grimoire f62b005
first
1bc41d4
load model weights
a27e72d
wip
cffce51
done
2685491
support shared kv
68a48f7
pre-alloc output
10d8a6f
fix ut
c53f5ce
enlarge num warps
44dd1b4
add warning
grimoire e9bc9fc
update mha kernel
grimoire b86244f
dynamic share kv
e65a5e0
adjust num warps
839fc43
autotuning
c0677b7
support lite
b332dd8
remove autotune
grimoire 41277f2
split dmodel
grimoire e946014
inplace rms
grimoire a0d0141
merge main
grimoire 5967ce4
solve conflict
d18af8f
Merge branch 'main' into torch-deepseek-v2
62033ae
merge main
7644b9c
merge main
34ad3df
solve conflict
203c3be
update support model
995e0ed
fix ut
473283d
update block size automatically
e21eaa0
merge main
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
Oops, something went wrong.
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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Will this affect models other than DeepSeek v2?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, the mha kernel needs enough smem to cache the kv_cache block and query block. Any model with such a large head_dim should be limited.
Among all the models that Pytorch engine has supported, only deepseek v2 with MLA implementation meets the condition.