[PyTorch Edge] Remove Original Weight Tensor from QNNPack Sparse Quantized Linear Packed Params #80473
Conversation
…tized Linear Packed Params We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it Differential Revision: [D34617321](https://our.internmc.facebook.com/intern/diff/D34617321/) [ghstack-poisoned]
🔗 Helpful links
✅ No Failures (0 Pending)As of commit dd5d077 (more details on the Dr. CI page): Expand to see more💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
…Sparse Quantized Linear Packed Params" We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it Differential Revision: [D34617321](https://our.internmc.facebook.com/intern/diff/D34617321/) [ghstack-poisoned]
…Sparse Quantized Linear Packed Params" We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it Differential Revision: [D34617321](https://our.internmc.facebook.com/intern/diff/D34617321/) [ghstack-poisoned]
…Sparse Quantized Linear Packed Params" We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it Differential Revision: [D34617321](https://our.internmc.facebook.com/intern/diff/D34617321/) [ghstack-poisoned]
…Sparse Quantized Linear Packed Params" We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it Differential Revision: [D34617321](https://our.internmc.facebook.com/intern/diff/D34617321/) [ghstack-poisoned]
|
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
|
@pytorchbot successfully started a merge job. Check the current status here |
|
Hey @salilsdesai. |
…tized Linear Packed Params (#80473) Summary: Pull Request resolved: #80473 We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it ghstack-source-id: 160768056 Test Plan: Phabricator tests Reviewed By: kimishpatel, junesg Differential Revision: D34617321 fbshipit-source-id: c3d14fba887bc705f2e10dd903ca64f239cdac03
4 participants
Stack from ghstack (oldest at bottom):
We plan to add serialization/deserialization wihout the original weight tensor, so we no longer need to store it
Differential Revision: D34617321