add t4

huggingface · Aug 1, 2024 · 6a4bf71 · 6a4bf71
1 parent a4272c3
commit 6a4bf71
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 3 deletions.
diff --git a/.github/workflows/update_llm_perf_cuda_pytorch.yaml b/.github/workflows/update_llm_perf_cuda_pytorch.yaml
@@ -21,8 +21,11 @@ jobs:
       fail-fast: false
       matrix:
         subset: [unquantized, bnb, awq, gptq]
-        # { name: 1xA10, runs-on: ... }, 
-        machine: [{ name: 1xT4, runs-on: { group: 'aws-g4dn-2xlarge' } }]
+
+        machine: [
+        # {name: 1xA10, runs-on: {group: 'aws-g5-4xlarge-plus'}}, 
+          {name: 1xT4, runs-on: {group: 'aws-g4dn-2xlarge'}}
+        ]
 
     runs-on: ${{ matrix.machine.runs-on }}
 

diff --git a/llm_perf/update_llm_perf_leaderboard.py b/llm_perf/update_llm_perf_leaderboard.py
@@ -32,7 +32,7 @@ def gather_benchmarks(subset: str, machine: str):
 
 def update_perf_dfs():
     for subset in ["unquantized", "bnb", "awq", "gptq"]:
-        for machine in ["1xA10", "1xA100"]:
+        for machine in ["1xA10", "1xA100", "1xT4"]:
             try:
                 gather_benchmarks(subset, machine)
             except Exception: