Skip to content

support quantisation with v5.1 hashes + env variable fixes #619

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 3 commits into from
Sep 14, 2025
Merged

support quantisation with v5.1 hashes + env variable fixes #619

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
529c914
Support quantisation - r5.1
anandhu-eng Sep 13, 2025
b08af65
fix issue with env
anandhu-eng Sep 13, 2025
8653fc0
fix typo
anandhu-eng Sep 13, 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
6 changes: 3 additions & 3 deletions script/get-ml-model-llama2/customize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,8 @@ def preprocess(i):
os_info = i['os_info']
env = i['env']

if env.get('MLC_TMP_ML_MODEL_QUANTIZE_LOCALLY', '') == 'nvidia':
if is_true(env.get('MLC_ML_MODEL_QUANTIZE_LOCALLY')):
if env.get('MLC_TMP_ML_MODEL_PROVIDER', '') == 'nvidia':
if is_true(env.get('MLC_TMP_ML_MODEL_QUANTIZE_LOCALLY')):
i['run_script_input']['script_name'] = 'run-nvidia'
gpu_arch = int(
float(
Expand Down Expand Up @@ -63,7 +63,7 @@ def postprocess(i):

env = i['env']
if env.get('MLC_DOWNLOAD_MODE', '') != "dry":
if is_true(env.get('MLC_ML_MODEL_QUANTIZE_LOCALLY')):
if is_true(env.get('MLC_TMP_ML_MODEL_QUANTIZE_LOCALLY')):
if env.get('LLAMA2_CHECKPOINT_PATH', '') == '':
env['LLAMA2_CHECKPOINT_PATH'] = env['MLC_ML_MODEL_PATH']
else:
Expand Down
8 changes: 8 additions & 0 deletions script/get-ml-model-llama2/meta.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -275,6 +275,12 @@ variations:
MLC_GIT_CHECKOUT_PATH_ENV_NAME: MLC_TENSORRT_LLM_CHECKOUT_PATH
extra_cache_tags: tensorrt-llm
tags: get,git,repo,_repo.https://github.com/NVIDIA/TensorRT-LLM.git,_sha.2ea17cdad28bed0f30e80eea5b1380726a7c6493,_submodules.3rdparty/NVTX;3rdparty/cutlass;3rdparty/cxxopts;3rdparty/json;3rdparty/pybind11;3rdparty/ucxx;3rdparty/xgrammar
pytorch,nvidia,v5.1,quantize-locally:
deps:
- env:
MLC_GIT_CHECKOUT_PATH_ENV_NAME: MLC_TENSORRT_LLM_CHECKOUT_PATH
extra_cache_tags: tensorrt-llm
tags: get,git,repo,_repo.https://github.com/NVIDIA/TensorRT-LLM.git,_branch.1.0-mlpinf,_sha.18c0333e96ea7a2c37caded8a310d05c5f095e88,_submodules.3rdparty/NVTX;3rdparty/cutlass;3rdparty/cxxopts;3rdparty/json;3rdparty/pybind11;3rdparty/ucxx;3rdparty/xgrammar
pytorch,nvidia,quantize-locally:
default_variations:
precision: fp8
Expand Down Expand Up @@ -317,3 +323,5 @@ variations:
v5.0:
group: version
default: true
v5.1:
group: version
Loading