[PT2]: Add Static Dispatch Kernel for wrapped_fbgemm_linear_fp16_weight #160451
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/160451
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 7a6e78b with merge base dae7710 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D80042054 |
Attention! native_functions.yaml was changedIf you are adding a new function or defaulted argument to native_functions.yaml, you cannot use it from pre-existing Python frontend code until our FC window passes (two weeks). Split your PR into two PRs, one which adds the new C++ functionality, and one that makes use of it from Python, and land them two weeks apart. See https://github.com/pytorch/pytorch/wiki/PyTorch's-Python-Frontend-Backward-and-Forward-Compatibility-Policy#forwards-compatibility-fc for more info. Caused by: |
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 12, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 13, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 13, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 13, 2025
…pytorch#160451) Summary: Pull Request resolved: pytorch#160451 Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
|
This pull request was exported from Phabricator. Differential Revision: D80042054 |
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 13, 2025
…pytorch#160451) Summary: Pull Request resolved: pytorch#160451 Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 13, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 13, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
|
This pull request was exported from Phabricator. Differential Revision: D80042054 |
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 14, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 14, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 14, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
|
This pull request was exported from Phabricator. Differential Revision: D80042054 |
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 14, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 14, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
|
This pull request was exported from Phabricator. Differential Revision: D80042054 |
kqfu
added a commit
to kqfu/pytorch
that referenced
this pull request
Aug 14, 2025
…pytorch#160451) Summary: Pull Request resolved: pytorch#160451 Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
|
/easycla |
henryoier
approved these changes
Aug 15, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054
|
This pull request was exported from Phabricator. Differential Revision: D80042054 |
|
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
can-gaa-hou
pushed a commit
to can-gaa-hou/pytorch
that referenced
this pull request
Aug 22, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054 Pull Request resolved: pytorch#160451 Approved by: https://github.com/henryoier
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
…ht (pytorch#160451) Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid. Test Plan: ``` MODEL_TYPE=dpa_product_first_ctr_model MODEL_ENTITY_ID=892669089 SNAPSHOT_ID=37 OTHER_MODEL_ENTITY_ID=892669089 OTHER_SNAPSHOT_ID=36 MODULES=(mix prepare_float_features object user) SUFFIXES=(.predictor.local .predictor.precompute.prepare_float_features .predictor.precompute.remote_object_only .predictor.precompute.remote_request_only) for i in "${!MODULES[@]}"; do MODULE=${MODULES[i]} SUFFIX=${SUFFIXES[i]} buck2 run mode/opt caffe2/torch/fb/model_transform/fx2trt/packaging:load_net_predictor -- --loadMode=BenchmarkAB --inputNetFile=/data/users/$USER/models/${MODEL_ENTITY_ID}/${SNAPSHOT_ID}/${MODEL_ENTITY_ID}_${SNAPSHOT_ID}${SUFFIX} --otherNetFile=/data/users/$USER/models/${OTHER_MODEL_ENTITY_ID}/${OTHER_SNAPSHOT_ID}/${OTHER_MODEL_ENTITY_ID}_${OTHER_SNAPSHOT_ID}${SUFFIX} --moduleName=${MODULE} --submodToDevice "" --benchmarkDontRebatchSamples=true --doNotRandomizeSampleInputs=true ``` Before: P1900475429 I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms After: P1900825771 I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m Still has some regression but the gap is smaller... Rollback Plan: Reviewed By: henryoier, muchulee8 Differential Revision: D80042054 Pull Request resolved: pytorch#160451 Approved by: https://github.com/henryoier
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary: Add static dispatch kernel for wrapped_fbgemm_linear_fp16_weight. This optimization should improve perf for all Ads DSNN models using Sigmoid.
Test Plan:
Before: P1900475429
I0810 19:29:22.782902 2717337 load_net_predictor_lib.cpp:1807] Average latency A: 0.0843 ms
I0810 19:29:22.782905 2717337 load_net_predictor_lib.cpp:1807] Average latency B: 0.0989 ms
After: P1900825771
I0811 15:42:34.866408 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency A: 0.0854 ms[0m
I0811 15:42:34.866411 2311279 load_net_predictor_lib.cpp:1807] [36mAverage latency B: 0.092 ms[0m
Still has some regression but the gap is smaller...
Rollback Plan:
Reviewed By: henryoier, muchulee8
Differential Revision: D80042054