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
[Quant] [PT2] Enable Decomposed quant per tensor/channel to accept bfloat16 input #112225
[Quant] [PT2] Enable Decomposed quant per tensor/channel to accept bfloat16 input #112225
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/112225
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 89133ba with merge base 871e27a (): UNSTABLE - The following job failed but was likely due to flakiness present on trunk and has been marked as unstable:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
ghstack-source-id: 5ffd0718d48982432c98ff852d90d65021b83ec9 Pull Request resolved: #112225
…float16 input" **Summary** Enable `decomposed quant_per_tensor` and `quant_per_channel` accepts bfloat16 input. **TestPlan** ``` python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_tensor_bfloat16_input python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_channel_bfloat16_input ``` [ghstack-poisoned]
ghstack-source-id: 68b017b5a02de389cc8e238c4b71089c8051ac18 Pull Request resolved: #112225
…o accept bfloat16 input" **Summary** - PR 4 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable `decomposed quant_per_tensor` and `quant_per_channel` accepts bfloat16 input. **TestPlan** ``` python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_tensor_bfloat16_input python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_channel_bfloat16_input ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
ghstack-source-id: dfcf5ff1baa403210254d5b5f9a1cd1b92b51816 Pull Request resolved: pytorch#112225
ghstack-source-id: dfcf5ff1baa403210254d5b5f9a1cd1b92b51816 Pull Request resolved: pytorch#112225
…o accept bfloat16 input" **Summary** - PR 4 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable `decomposed quant_per_tensor` and `quant_per_channel` accepts bfloat16 input. **TestPlan** ``` python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_tensor_bfloat16_input python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_channel_bfloat16_input ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
ghstack-source-id: 938f4dc617b28a2e66eac36cec326596ed7e50c9 Pull Request resolved: pytorch#112225
@pytorchbot merge |
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 |
Merge failedReason: 1 jobs have failed, first few of them are: trunk / macos-12-py3-arm64 / test (default, 1, 3, macos-m1-12) Details for Dev Infra teamRaised by workflow job |
…o accept bfloat16 input" **Summary** - PR 4 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable `decomposed quant_per_tensor` and `quant_per_channel` accepts bfloat16 input. **TestPlan** ``` python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_tensor_bfloat16_input python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_channel_bfloat16_input ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
@pytorchbot merge |
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 |
…loat16 input (pytorch#112225) **Summary** - PR 4 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor pytorch#111640. - Enable `decomposed quant_per_tensor` and `quant_per_channel` accepts bfloat16 input. **TestPlan** ``` python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_tensor_bfloat16_input python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_channel_bfloat16_input ``` Pull Request resolved: pytorch#112225 Approved by: https://github.com/jgong5, https://github.com/jerryzh168
…loat16 input (pytorch#112225) **Summary** - PR 4 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor pytorch#111640. - Enable `decomposed quant_per_tensor` and `quant_per_channel` accepts bfloat16 input. **TestPlan** ``` python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_tensor_bfloat16_input python -m pytest test_quantized_tensor.py -k test_decomposed_quantize_per_channel_bfloat16_input ``` Pull Request resolved: pytorch#112225 Approved by: https://github.com/jgong5, https://github.com/jerryzh168
Stack from ghstack (oldest at bottom):
Summary
decomposed quant_per_tensor
andquant_per_channel
accepts bfloat16 input.TestPlan
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler