Skip to content

Fixes for Nvidia gptj #352

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 4 commits into from
Apr 7, 2025
Merged

Fixes for Nvidia gptj #352

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
13e4a72
Added version fix for nvidia TRTLLM
arjunsuresh Apr 7, 2025
c35256e
Added version fix for nvidia TRTLLM
arjunsuresh Apr 7, 2025
0564c39
Added version fix for nvidia TRTLLM
arjunsuresh Apr 7, 2025
af87370
Fix nvidia gptj
arjunsuresh Apr 7, 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
2 changes: 1 addition & 1 deletion script/app-mlperf-inference-nvidia/customize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -300,7 +300,7 @@ def preprocess(i):
if not os.path.exists(fp32_model_path):
# download via prehook_deps
env['MLC_REQUIRE_GPTJ_MODEL_DOWNLOAD'] = 'yes'
if make_command == "build_engine":
if make_command in ["build_engine", "preprocess_data"]:
cmds.append(
f"cp -r $MLC_ML_MODEL_FILE_WITH_PATH {fp32_model_path}")

Expand Down
9 changes: 9 additions & 0 deletions script/app-mlperf-inference/meta.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -404,6 +404,15 @@ variations:
_tp-size.:
- MLC_NVIDIA_TP_SIZE

nvidia-original,r5.0-dev_default,gptj_:
docker:
image_name: mlperf-inference-nvidia-v4.1-dev-llm
deps:
- tags: get,ml-model,gptj,_nvidia,_fp8
update_tags_from_env_with_prefix:
_tp-size.:
- MLC_NVIDIA_TP_SIZE

nvidia-original,r4.1_default:
docker:
base_image: nvcr.io/nvidia/mlperf/mlperf-inference:mlpinf-v4.1-cuda12.4-pytorch24.04-ubuntu22.04-x86_64-release
Expand Down
16 changes: 16 additions & 0 deletions script/build-mlperf-inference-server-nvidia/meta.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,13 +276,29 @@ versions:
- x86_64
MLC_PYTHON_MINOR_VERSION:
- 8
- tags: get,generic-python-lib,_package.cuda-python
names:
- cuda-python
version_max: '12.6'
version_max_usable: '12.3.0'
- tags: get,generic-python-lib,_package.networkx
version_max: '2.9.99'
version_max_usable: '2.8.8'

r4.1-dev:
default_env:
BUILD_TRTLLM: 1
deps:
- tags: get,generic,sys-util,_nlohmann-json3-dev
- tags: get,generic,sys-util,_git-lfs
- tags: get,generic-python-lib,_package.cuda-python
names:
- cuda-python
version_max: '12.6'
version_max_usable: '12.3.0'
- tags: get,generic-python-lib,_package.networkx
version_max: '2.9.99'
version_max_usable: '2.8.8'
- tags: install,pytorch,from.src,_for-nvidia-mlperf-inference-v4.0
names:
- pytorch
Expand Down
Loading