-
Notifications
You must be signed in to change notification settings - Fork 1.7k
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
[SLM] Batched Llama #1520
Merged
Merged
[SLM] Batched Llama #1520
Conversation
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
1e811f6
to
2295999
Compare
junrushao
reviewed
Jan 1, 2024
junrushao
reviewed
Jan 1, 2024
junrushao
reviewed
Jan 1, 2024
junrushao
reviewed
Jan 1, 2024
junrushao
reviewed
Jan 1, 2024
junrushao
reviewed
Jan 1, 2024
090d6eb
to
6eb18f4
Compare
747cd93
to
6d6357f
Compare
junrushao
reviewed
Jan 3, 2024
junrushao
reviewed
Jan 3, 2024
junrushao
reviewed
Jan 3, 2024
junrushao
reviewed
Jan 3, 2024
junrushao
reviewed
Jan 3, 2024
junrushao
reviewed
Jan 3, 2024
e1cc139
to
08874b8
Compare
junrushao
reviewed
Jan 4, 2024
junrushao
reviewed
Jan 4, 2024
319ce79
to
4f2a69f
Compare
junrushao
approved these changes
Jan 4, 2024
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.
LGTM!
This PR introduces the batched llama modeling with Paged KV cache in SLM flow.
9292f62
to
27cd520
Compare
tqchen
approved these changes
Jan 4, 2024
MasterJH5574
added a commit
that referenced
this pull request
Jan 4, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
that referenced
this pull request
Jan 4, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
that referenced
this pull request
Jan 4, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
that referenced
this pull request
Jan 4, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
that referenced
this pull request
Jan 4, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
junrushao
pushed a commit
that referenced
this pull request
Jan 4, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
to MasterJH5574/mlc-llm
that referenced
this pull request
Jan 10, 2024
PR mlc-ai#1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
that referenced
this pull request
Jan 10, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
MasterJH5574
added a commit
to MasterJH5574/mlc-llm
that referenced
this pull request
Jan 12, 2024
PR mlc-ai#1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
tqchen
pushed a commit
that referenced
this pull request
Jan 12, 2024
PR #1520 introduces batched llama to SLM. This PR updates the serving codebase and fully switch the model definition to SLM flow. Most changes in this PR are trivial. Note that with this PR merged in, the previous batching model definition flow becomes outdated and no longer usable.
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.
This PR introduces the batched llama modeling with Paged KV cache in SLM flow.