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

added min system requirements for models #17

Merged
merged 2 commits into from
Aug 23, 2024
Merged

added min system requirements for models #17

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e6abadd
added min system requirements for models
anandhu-eng Aug 23, 2024
8db76b4
Merge branch 'master' into cm_readme_inference_update
anandhu-eng Aug 23, 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
52 changes: 52 additions & 0 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,9 @@ def mlperf_inference_implementation_readme(spaces, model, implementation):
content += f"{cur_space1}=== \"{device}\"\n"
content += f"{cur_space2}##### {device} device\n\n"

# minimum system requirements
content += get_min_system_requirements(cur_space2, model, implementation, device)

# to select the execution environments(currently Docker and Native)
for execution_env in execution_envs:
if (device == "ROCm" or implementation == "qualcomm") and execution_env == "Docker":
Expand Down Expand Up @@ -213,6 +216,55 @@ def get_test_query_count(model, implementation, device, num_devices=1):
p_range *= num_devices

return p_range

def get_min_system_requirements(spaces, model, implementation, device):
model = model.lower()
min_sys_req_content = ""
min_sys_req_content += f"{spaces}<details>\n"
min_sys_req_content += f"{spaces}<summary>Please click here to see the minimum system requirements for running the benchmark</summary>\n\n"
# device memory
if device.lower() == "cuda" and (implementation.lower() == "nvidia" or implementation.lower() == "reference"):
if implementation.lower() == "nvidia":
if "dlrm" in model:
device_memory = "24GB"
elif "llama2-70b" in model or "mixtral" in model:
device_memory = "80GB"
elif "sdxl" in model or "gptj" in model:
device_memory = "16GB"
else:
device_memory = "8GB"
elif implementation.lower() == "reference":
if "dlrm" in model:
device_memory = "2x80GB"
elif "llama2-70b" in model:
device_memory = "8x80GB"
elif "mixtral" in model:
device_memory = "4x80GB"
elif "sdxl" in model:
device_memory = "24GB(fp32), 16GB(fp16)"
elif "gptj" in model:
device_memory = "80GB(fp32). 40GB(fp16)"
else:
device_memory = "8GB"
min_sys_req_content += f"{spaces}* **Device Memory**: {device_memory}\n\n"
# disk space
if "dlrm" in model:
disk_space = "500GB"
elif "llama2-70b" in model:
disk_space = "700GB"
elif "mixtral" in model:
disk_space = "100GB"
elif "retinanet" in model:
disk_space = "200GB"
else:
disk_space = "50GB"
min_sys_req_content += f"{spaces}* **Disk Space**: {disk_space}\n\n"
# System memory
if "dlrm" in model:
system_memory = "512GB"
min_sys_req_content += f"{spaces}* **System Memory(RAM+SWAP)**: {system_memory}\n\n"
min_sys_req_content += f"{spaces}</details>\n"
return min_sys_req_content

def get_readme_prefix(spaces, model, implementation):
readme_prefix = ""
Expand Down
Loading