Skip to content

Add local optoin for output json file #1426

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.

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
Dec 17, 2024
Merged

Add local optoin for output json file #1426

merged 2 commits into from
Dec 17, 2024

Conversation

jerryzh168
Copy link
Contributor

Summary:
We are planning to run the benchmarks in local machine for now since there are some issues when trying to run in OSS CI, so we have to fill in some fields that is populated by the OSS CI before

Test Plan:

python torchao/_models/llama/generate.py --checkpoint_path "${CHECKPOINT_PATH}/${MODEL_REPO}/model.pth" --compile --compile_prefill --output_json_path benchmark-results.json --output_json_local

python torchao/_models/llama/generate.py --checkpoint_path "${CHECKPOINT_PATH}/${MODEL_REPO}/model.pth" --compile --compile_prefill --quantization autoquant --output_json_path benchmark-results.json --output_js\on_local

python torchao/_models/sam/eval_combo.py --coco_root_dir datasets/coco2017 --coco_slice_name val2017 --sam_checkpoint_base_path checkpoints --sam_model_type vit_h --point_sampling_cache_dir tmp/sam_coco_mask_ce\nter_cache --mask_debug_out_dir tmp/sam_eval_masks_out --batch_size 32 --num_workers 8 --use_compile max-autotune --use_half bfloat16 --device cuda --output_json_path benchmark-results.json --output_json_local

python torchao/_models/sam/eval_combo.py --coco_root_dir datasets/coco2017 --coco_slice_name val2017 --sam_checkpoint_base_path checkpoints --sam_model_type vit_h --point_sampling_cache_dir tmp/sam_coco_mask_ce\nter_cache --mask_debug_out_dir tmp/sam_eval_masks_out --batch_size 32 --num_workers 8 --use_compile max-autotune --use_half bfloat16 --device cuda --compression autoquant --output_json_path benchmark-results.j\son --output_json_local

cd examples/sam2_amg_server
python server.py ${CHECKPOINT_PATH}/sam2 large --port 4000 --host localhost --fast --benchmark --dry --output_json_path ../../benchmark-results.json --output_json_local
python server.py ${CHECKPOINT_PATH}/sam2 large --port 4000 --host localhost --fast --use_autoquant --benchmark --dry --output_json_path ../../benchmark-results.json --output_json_local
cd ../..

Reviewers:

Subscribers:

Tasks:

Tags:

Summary:
We are planning to run the benchmarks in local machine for now since there are some issues when trying to run in OSS CI,
so we have to fill in some fields that is populated by the OSS CI before

Test Plan:
```
python torchao/_models/llama/generate.py --checkpoint_path "${CHECKPOINT_PATH}/${MODEL_REPO}/model.pth" --compile --compile_prefill --output_json_path benchmark-results.json --output_json_local

python torchao/_models/llama/generate.py --checkpoint_path "${CHECKPOINT_PATH}/${MODEL_REPO}/model.pth" --compile --compile_prefill --quantization autoquant --output_json_path benchmark-results.json --output_js\on_local

python torchao/_models/sam/eval_combo.py --coco_root_dir datasets/coco2017 --coco_slice_name val2017 --sam_checkpoint_base_path checkpoints --sam_model_type vit_h --point_sampling_cache_dir tmp/sam_coco_mask_ce\nter_cache --mask_debug_out_dir tmp/sam_eval_masks_out --batch_size 32 --num_workers 8 --use_compile max-autotune --use_half bfloat16 --device cuda --output_json_path benchmark-results.json --output_json_local

python torchao/_models/sam/eval_combo.py --coco_root_dir datasets/coco2017 --coco_slice_name val2017 --sam_checkpoint_base_path checkpoints --sam_model_type vit_h --point_sampling_cache_dir tmp/sam_coco_mask_ce\nter_cache --mask_debug_out_dir tmp/sam_eval_masks_out --batch_size 32 --num_workers 8 --use_compile max-autotune --use_half bfloat16 --device cuda --compression autoquant --output_json_path benchmark-results.j\son --output_json_local

cd examples/sam2_amg_server
python server.py ${CHECKPOINT_PATH}/sam2 large --port 4000 --host localhost --fast --benchmark --dry --output_json_path ../../benchmark-results.json --output_json_local
python server.py ${CHECKPOINT_PATH}/sam2 large --port 4000 --host localhost --fast --use_autoquant --benchmark --dry --output_json_path ../../benchmark-results.json --output_json_local
cd ../..
```
Reviewers:

Subscribers:

Tasks:

Tags:
Copy link

pytorch-bot bot commented Dec 17, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1426

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit a915093 with merge base cbd7c29 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Dec 17, 2024
@jerryzh168 jerryzh168 added the topic: not user facing Use this tag if you don't want this PR to show up in release notes label Dec 17, 2024
@jerryzh168 jerryzh168 merged commit a5a53a2 into main Dec 17, 2024
18 of 19 checks passed
amdfaa pushed a commit that referenced this pull request Jan 10, 2025
* Add local optoin for output json file

Summary:
We are planning to run the benchmarks in local machine for now since there are some issues when trying to run in OSS CI,
so we have to fill in some fields that is populated by the OSS CI before

Test Plan:
```
python torchao/_models/llama/generate.py --checkpoint_path "${CHECKPOINT_PATH}/${MODEL_REPO}/model.pth" --compile --compile_prefill --output_json_path benchmark-results.json --output_json_local

python torchao/_models/llama/generate.py --checkpoint_path "${CHECKPOINT_PATH}/${MODEL_REPO}/model.pth" --compile --compile_prefill --quantization autoquant --output_json_path benchmark-results.json --output_js\on_local

python torchao/_models/sam/eval_combo.py --coco_root_dir datasets/coco2017 --coco_slice_name val2017 --sam_checkpoint_base_path checkpoints --sam_model_type vit_h --point_sampling_cache_dir tmp/sam_coco_mask_ce\nter_cache --mask_debug_out_dir tmp/sam_eval_masks_out --batch_size 32 --num_workers 8 --use_compile max-autotune --use_half bfloat16 --device cuda --output_json_path benchmark-results.json --output_json_local

python torchao/_models/sam/eval_combo.py --coco_root_dir datasets/coco2017 --coco_slice_name val2017 --sam_checkpoint_base_path checkpoints --sam_model_type vit_h --point_sampling_cache_dir tmp/sam_coco_mask_ce\nter_cache --mask_debug_out_dir tmp/sam_eval_masks_out --batch_size 32 --num_workers 8 --use_compile max-autotune --use_half bfloat16 --device cuda --compression autoquant --output_json_path benchmark-results.j\son --output_json_local

cd examples/sam2_amg_server
python server.py ${CHECKPOINT_PATH}/sam2 large --port 4000 --host localhost --fast --benchmark --dry --output_json_path ../../benchmark-results.json --output_json_local
python server.py ${CHECKPOINT_PATH}/sam2 large --port 4000 --host localhost --fast --use_autoquant --benchmark --dry --output_json_path ../../benchmark-results.json --output_json_local
cd ../..
```
Reviewers:

Subscribers:

Tasks:

Tags:

* fix
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: not user facing Use this tag if you don't want this PR to show up in release notes
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants