add llama-3.3-70b to 3 M4 Pro cluster

e5d54c77a91474822c631e5c704624caec2a4951 · 2024-12-12 18:51:26 +0000 · Alex Cheema

Files touched

M .github/workflows/benchmarks.yml

Diff

commit e5d54c77a91474822c631e5c704624caec2a4951
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Thu Dec 12 18:51:26 2024 +0000

    add llama-3.3-70b to 3 M4 Pro cluster
---
 .github/workflows/benchmarks.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/benchmarks.yml b/.github/workflows/benchmarks.yml
index e00b5dfd..2f797c8e 100644
--- a/.github/workflows/benchmarks.yml
+++ b/.github/workflows/benchmarks.yml
@@ -24,7 +24,7 @@ jobs:
   three-m4-pro-cluster:
     strategy:
       matrix:
-        model: ['llama-3.2-1b', 'llama-3.2-3b', 'llama-3.1-8b']
+        model: ['llama-3.2-1b', 'llama-3.2-3b', 'llama-3.1-8b', 'llama-3.3-70b']
       # Optional: add fail-fast: false if you want all matrix jobs to continue even if one fails
       fail-fast: false
     uses: ./.github/workflows/bench_job.yml

← a0bada3b add llama-3.2-1b-8bit, llama-3.2-3b-8bit, llama-3.2-3b-bf16 · back to Exo · fix counts in testmodelhelpers b0e079b3 →