qnn end to end flow #3038
Closed
qnn end to end flow #3038
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
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3038
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 357e94e with merge base 2c467dd ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced Apr 14, 2024
Closed
cccclai
added a commit
that referenced
this pull request
Apr 14, 2024
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) ghstack-source-id: 222465750 Pull Request resolved: #3038
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 14, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 222465994 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 14, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 222466043 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 14, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 222471499 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 14, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 222473434 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
cccclai
requested review from
haowhsu-quic,
shewu-quic,
chiwwang and
chunit-quic
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 15, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside in the sunshine. One day, she saw a big, red apple hanging from a tree. She wanted to eat it, but it was too high up.. ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 222613601 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 16, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 222650468 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 18, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223091081 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 19, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223136109 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 19, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223152097 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 19, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223153222 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
kimishpatel
approved these changes
Apr 19, 2024
kirklandsign
approved these changes
Apr 19, 2024
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 19, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223160858 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park. One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not. Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet. ``` Stories model is too small and sensitive to qunatization. Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D56119738 |
cccclai
added a commit
that referenced
this pull request
Apr 19, 2024
Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223199545 @exported-using-ghexport Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)
|
This pull request has been merged in 3257c66. |
cccclai
added a commit
that referenced
this pull request
Apr 19, 2024
Summary: Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223199545 exported-using-ghexport Reviewed By: mergennachin, kirklandsign Differential Revision: D56119738 fbshipit-source-id: daf5563fe51a677f302e09ae8a9fb80e6bda72c5 (cherry picked from commit 3257c66)
guangy10
pushed a commit
that referenced
this pull request
Apr 20, 2024
Summary: Pull Request resolved: #3038 Patch a few changes including: - support bool tensor type - support fp16 and fix the 8w8a quantization. - add two non-supported ops (slice_scatter and index_put) in common_defs.py stories model working end to end: AOT: fp16: ``` python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json ``` quantize: ``` python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize qnn_8a8w -c stories110M.pt -p params.json ``` Runtime: ``` /llama_main --model_path=llama2_fp16_qnn_2.21.pte --tokenizer_path=tokenizer.bin --prompt="Once" ``` Output: ``` Once upon a time, there was a little girl named Lily. She loved to play outside and explore the world around her. One day, she went on a walk with her mommy and they found a beautiful landscape with lots of trees and flowers. Lily said, "Mommy, this place is so pretty! Can we take a picture?" Mommy replied, "Of course, Lily! Let's take a picture to remember the original place we found." After they took the picture, they continued their walk and saw a bird flying in the sky. Lily said, "MomPyTorchObserver {"prompt_tokens":2,"generated_tokens":125,"model_load_start_ms":1713226585936,"model_load_end_ms":1713226586909,"inference_start_ms":1713226586909,"inference_end_ms":1713226590363,"prompt_eval_end_ms":1713226586966,"first_token_ms":1713226586994,"aggregate_sampling_time_ms":23,"SCALING_FACTOR_UNITS_PER_SECOND":1000} I 00:00:04.436699 executorch:runner.cpp:414] Prompt Tokens: 2 Generated Tokens: 125 I 00:00:04.436703 executorch:runner.cpp:420] Model Load Time: 0.973000 (seconds) I 00:00:04.436732 executorch:runner.cpp:430] Total inference time: 3.454000 (seconds) Rate: 36.189925 (tokens/second) I 00:00:04.436735 executorch:runner.cpp:438] Prompt evaluation: 0.057000 (seconds) Rate: 35.087719 (tokens/second) I 00:00:04.436739 executorch:runner.cpp:449] Generated 125 tokens: 3.397000 (seconds) Rate: 36.797174 (tokens/second) I 00:00:04.436742 executorch:runner.cpp:457] Time to first generated token: 0.085000 (seconds) I 00:00:04.436744 executorch:runner.cpp:464] Sampling time over 127 tokens: 0.023000 (seconds) [INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters [INFO] [Qnn ExecuTorch]: Destroy Qnn context ``` Stories model is too small and sensitive to qunatization. ghstack-source-id: 223199545 exported-using-ghexport Reviewed By: mergennachin, kirklandsign Differential Revision: D56119738 fbshipit-source-id: daf5563fe51a677f302e09ae8a9fb80e6bda72c5 (cherry picked from commit 3257c66)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Stack from ghstack (oldest at bottom):
Patch a few changes including:
stories model working end to end:
AOT:
fp16:
quantize:
Runtime:
Output:
Stories model is too small and sensitive to qunatization.
Differential Revision: D56119738