Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Add profiling support for paged attn #585

Draft
wants to merge 2 commits into
base: master
Choose a base branch
from
+11 −0
Draft

Add profiling support for paged attn #585

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8b50134
Stub
EricLBuehler Jul 17, 2024
1b197c1
Stub
EricLBuehler Jul 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions mistralrs-core/src/pipeline/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,10 +10,12 @@ mod normal;
mod normal_loaders;
mod paths;
mod processing;
mod profile;
mod sampling;
mod speculative;
mod vision;
mod vision_loaders;

use crate::aici::toktree::TokTrie;
use crate::amoe::{
AnyMoeBaseModelMixin, AnyMoeConfig, AnyMoeExpertType, AnyMoeTrainingInputs,
Expand Down
9 changes: 9 additions & 0 deletions mistralrs-core/src/pipeline/profile.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
use crate::{PagedAttentionConfig, Pipeline};

pub fn profile(

Check failure on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Clippy 

function `profile` is never used

Check warning on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (macOS-latest, stable) 

function `profile` is never used

Check warning on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (ubuntu-latest, stable) 

function `profile` is never used

Check warning on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Docs 

function `profile` is never used

Check warning on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (macOS-latest, stable) 

function `profile` is never used

Check warning on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (windows-latest, stable) 

function `profile` is never used

Check warning on line 3 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (ubuntu-latest, stable) 

function `profile` is never used
pipeline: &dyn Pipeline,

Check failure on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Clippy 

unused variable: `pipeline`

Check warning on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (macOS-latest, stable) 

unused variable: `pipeline`

Check warning on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (ubuntu-latest, stable) 

unused variable: `pipeline`

Check warning on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Docs 

unused variable: `pipeline`

Check warning on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (macOS-latest, stable) 

unused variable: `pipeline`

Check warning on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (windows-latest, stable) 

unused variable: `pipeline`

Check warning on line 4 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (ubuntu-latest, stable) 

unused variable: `pipeline`
block_size: Option<usize>,

Check failure on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Clippy 

unused variable: `block_size`

Check warning on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (macOS-latest, stable) 

unused variable: `block_size`

Check warning on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (ubuntu-latest, stable) 

unused variable: `block_size`

Check warning on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Docs 

unused variable: `block_size`

Check warning on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (macOS-latest, stable) 

unused variable: `block_size`

Check warning on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (windows-latest, stable) 

unused variable: `block_size`

Check warning on line 5 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (ubuntu-latest, stable) 

unused variable: `block_size`
max_num_batched_tokens: Option<usize>,

Check failure on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Clippy 

unused variable: `max_num_batched_tokens`

Check warning on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (macOS-latest, stable) 

unused variable: `max_num_batched_tokens`

Check warning on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (ubuntu-latest, stable) 

unused variable: `max_num_batched_tokens`

Check warning on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Docs 

unused variable: `max_num_batched_tokens`

Check warning on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (macOS-latest, stable) 

unused variable: `max_num_batched_tokens`

Check warning on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Check (windows-latest, stable) 

unused variable: `max_num_batched_tokens`

Check warning on line 6 in mistralrs-core/src/pipeline/profile.rs

View workflow job for this annotation

GitHub Actions / Test Suite (ubuntu-latest, stable) 

unused variable: `max_num_batched_tokens`
) -> PagedAttentionConfig {
todo!()
}
Loading