[MLC-LLM] Separate function for generating sharding PrimFunc #250
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
Lunderberg
pushed a commit
to Lunderberg/mlc-llm
that referenced
this pull request
Apr 1, 2024
Lunderberg
force-pushed
the
lunderberg/expose_sharding_primfunc_generation
branch
from
a42491e to
2d2c253
Compare
Author
|
Rebased onto |
The `create_shard_func` produces both the `tir.PrimFunc` that performs the sharding and a `relax.Function` wrapper that calls into it. This separates out the two functions, such that the `tir.PrimFunc` can be generated without also generating the `relax.Function` wrapper.
Lunderberg
force-pushed
the
lunderberg/expose_sharding_primfunc_generation
branch
from
2d2c253 to
f1bddee
Compare
sunggg
changed the title
sunggg
approved these changes
Apr 12, 2024
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Outdated suggestions cannot be applied.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.
The
create_shard_funcproduces both thetir.PrimFuncthat performs the sharding and arelax.Functionwrapper that calls into it. This separates out the two functions, such that thetir.PrimFunccan be generated without also generating therelax.Functionwrapper.