Skip to content

[ROCm CI] Migrate to MI325 Capacity #60

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

Merged
merged 2 commits into from
Aug 2, 2025
Merged

[ROCm CI] Migrate to MI325 Capacity #60

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
4f2ed51
[ROCm CI] Migrate to MI325 Capacity
amdfaa Aug 2, 2025
972f856
Update generate_vllm_benchmark_matrix.py
amdfaa Aug 2, 2025
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
14 changes: 7 additions & 7 deletions .github/scripts/generate_vllm_benchmark_matrix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,24 +16,24 @@
1: [
"linux.aws.a100",
"linux.aws.h100",
"linux.rocm.gpu.mi300.2", # No single ROCm GPU?
"linux.rocm.gpu.gfx942.2", # No single ROCm GPU?
"linux.24xl.spr-metal",
],
# NB: There is no 2xH100 runner at the momement, so let's use the next one
# in the list here which is 4xH100
2: [
"linux.aws.h100.4",
"linux.rocm.gpu.mi300.2",
"linux.rocm.gpu.gfx942.2",
],
4: [
"linux.aws.h100.4",
"linux.rocm.gpu.mi300.4",
"linux.rocm.gpu.gfx942.4",
# TODO (huydhn): Enable this when Intel's runners are ready
# "intel-cpu-emr",
],
8: [
"linux.aws.h100.8",
"linux.rocm.gpu.mi300.8",
"linux.rocm.gpu.gfx942.8",
],
}

Expand All @@ -43,9 +43,9 @@
"linux.aws.h100": "cuda",
"linux.aws.h100.4": "cuda",
"linux.aws.h100.8": "cuda",
"linux.rocm.gpu.mi300.2": "rocm",
"linux.rocm.gpu.mi300.4": "rocm",
"linux.rocm.gpu.mi300.8": "rocm",
"linux.rocm.gpu.gfx942.2": "rocm",
"linux.rocm.gpu.gfx942.4": "rocm",
"linux.rocm.gpu.gfx942.8": "rocm",
"linux.24xl.spr-metal": "cpu",
}

Expand Down
28 changes: 14 additions & 14 deletions .github/scripts/test_generate_vllm_benchmark_matrix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,23 +46,23 @@ def test_generate_benchmark_matrix():
"models": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.4",
"runner": "linux.rocm.gpu.gfx942.4",
"models": "meta-llama/meta-llama-3.1-70b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "mistralai/mixtral-8x7b-instruct-v0.1"
},
{
"runner": "linux.rocm.gpu.mi300.4",
"runner": "linux.rocm.gpu.gfx942.4",
"models": "meta-llama/llama-4-scout-17b-16e-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.8",
"runner": "linux.rocm.gpu.gfx942.8",
"models": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
}
]
Expand All @@ -89,7 +89,7 @@ def test_generate_benchmark_matrix():
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
}
]
Expand Down Expand Up @@ -123,11 +123,11 @@ def test_generate_benchmark_matrix():
"models": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.8",
"runner": "linux.rocm.gpu.gfx942.8",
"models": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
}
]
Expand All @@ -154,7 +154,7 @@ def test_generate_benchmark_matrix():
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
}
]
Expand All @@ -181,7 +181,7 @@ def test_generate_benchmark_matrix():
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
}
]
Expand Down Expand Up @@ -370,11 +370,11 @@ def test_generate_benchmark_matrix():
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
},
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "mistralai/mixtral-8x7b-instruct-v0.1"
}
]
Expand All @@ -393,7 +393,7 @@ def test_generate_benchmark_matrix():
{
"include": [
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
}
]
Expand All @@ -412,7 +412,7 @@ def test_generate_benchmark_matrix():
{
"include": [
{
"runner": "linux.rocm.gpu.mi300.2",
"runner": "linux.rocm.gpu.gfx942.2",
"models": "meta-llama/meta-llama-3.1-8b-instruct"
}
]
Expand Down