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

Updations for DLRM-v2 #4

Merged
merged 2 commits into from
Aug 12, 2024
Merged

Updations for DLRM-v2 #4

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
0c94ea9
lower cased implementation
anandhu-eng Aug 12, 2024
5b0df15
added raw data input
anandhu-eng Aug 12, 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
4 changes: 2 additions & 2 deletions docs/benchmarks/language/llama2-70b.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ hide:
## Neural Magic MLPerf Implementation

LLAMA2-70b-99
{{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "NeuralMagic") }}
{{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "neuralmagic") }}

LLAMA2-70b-99.9
{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "NeuralMagic") }}
{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "neuralmagic") }}
12 changes: 6 additions & 6 deletions docs/benchmarks/recommendation/dlrm-v2.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,25 @@ hide:
## MLPerf Reference Implementation in Python

DLRM-v2-99
{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "reference") }}
{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "reference") }}

DLRM-v2-99.9
{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "reference") }}
{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "reference") }}

=== "Nvidia"
## Nvidia MLPerf Implementation

DLRM-v2-99
{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "nvidia") }}
{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "nvidia") }}

DLRM-v2-99.9
{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "nvidia") }}
{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "nvidia") }}

=== "Intel"
## Intel MLPerf Implementation

DLRM-v2-99
{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "intel") }}
{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "intel") }}

DLRM-v2-99.9
{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "intel") }}
{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "intel") }}
16 changes: 11 additions & 5 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,12 +34,12 @@ def mlperf_inference_implementation_readme(spaces, model, implementation):
devices = [ "CUDA" ]
frameworks = [ "TensorRT" ]

elif implementation == "NeuralMagic":
elif implementation == "neuralmagic":
devices = [ "CUDA" ]
frameworks = [ "vLLM" ]
frameworks = [ "pytorch" ]

elif implementation == "intel":
if model not in [ "bert-99", "bert-99.9", "gptj-99", "gptj-99.9", "resnet50", "retinanet", "3d-unet-99", "3d-unet-99.9", "dlrm_v2-99", "dlrm_v2-99.9" ]:
if model not in [ "bert-99", "bert-99.9", "gptj-99", "gptj-99.9", "resnet50", "retinanet", "3d-unet-99", "3d-unet-99.9", "dlrm-v2-99", "dlrm-v2-99.9" ]:
return pre_space+" WIP"
if model in [ "bert-99", "bert-99.9", "retinanet", "3d-unet-99", "3d-unet-99.9" ]:
code_version="r4.0"
Expand Down Expand Up @@ -269,11 +269,14 @@ def mlperf_inference_run_command(spaces, model, implementation, framework, categ
docker_cmd_suffix += f" \\\n{pre_space} --test_query_count={test_query_count}"

if "llama2-70b" in model:
if implementation != "NeuralMagic":
if implementation != "neuralmagic":
docker_cmd_suffix += f" \\\n{pre_space} --tp_size=<TP_SIZE>"
docker_cmd_suffix += f" \\\n{pre_space} --nvidia_llama2_dataset_file_path=<PATH_TO_PICKE_FILE>"
else:
docker_cmd_suffix += f" \\\n{pre_space} --api_server=<API_SERVER_URL>"

if "dlrm-v2" in model and implementation == "nvidia":
docker_cmd_suffix += f" \\\n{pre_space} --criteo_day23_raw_data_path=<PATH_TO_CRITEO_DAY23_RAW_DATA>"

docker_setup_cmd = f"""\n
{f_pre_space}```bash
Expand All @@ -295,11 +298,14 @@ def mlperf_inference_run_command(spaces, model, implementation, framework, categ
cmd_suffix += f" \\\n {pre_space} --test_query_count={test_query_count}"

if "llama2-70b" in model:
if implementation != "NeuralMagic":
if implementation != "neuralmagic":
cmd_suffix += f" \\\n{pre_space} --tp_size=<TP_SIZE>"
cmd_suffix += f" \\\n{pre_space} --nvidia_llama2_dataset_file_path=<PATH_TO_PICKE_FILE>"
else:
cmd_suffix += f" \\\n{pre_space} --api_server=<API_SERVER_URL>"

if "dlrm-v2" in model and implementation == "nvidia":
cmd_suffix += f" \\\n{pre_space} --criteo_day23_raw_data_path=<PATH_TO_CRITEO_DAY23_RAW_DATA>"

run_cmd = f"""\n
{f_pre_space}```bash
Expand Down
Loading