Add UIntxBitPackedTensor, UIntxWeightOnlyConfig, and Int8DynamicActivationUIntxWeightConfig#4081
Closed
jerryzh168 wants to merge 1 commit intogh/jerryzh168/47/basefrom
Closed
Add UIntxBitPackedTensor, UIntxWeightOnlyConfig, and Int8DynamicActivationUIntxWeightConfig#4081jerryzh168 wants to merge 1 commit intogh/jerryzh168/47/basefrom
jerryzh168 wants to merge 1 commit intogh/jerryzh168/47/basefrom
Conversation
…ationUIntxWeightConfig Add v2 tensor subclass UIntxBitPackedTensor(TorchAOBaseTensor) using gemlite bit-packing and Triton GEMM kernels, replacing the old AQT-based GemliteUIntXWeightOnlyConfig path. - UIntxBitPackedTensor: tensor subclass with from_hp(), dequantize(), and aten.linear/t/slice dispatch implementations - UIntxWeightOnlyConfig: weight-only quantization (4-bit/8-bit) - Int8DynamicActivationUIntxWeightConfig: int8 dynamic activation + uintx weight - Tests for both configs covering 4-bit, 8-bit, slice, and non-standard shapes [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/4081
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 9 PendingAs of commit 8e4bbdd with merge base ab4a336 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
jerryzh168
added a commit
that referenced
this pull request
Mar 13, 2026
…ationUIntxWeightConfig Add v2 tensor subclass UIntxBitPackedTensor(TorchAOBaseTensor) using gemlite bit-packing and Triton GEMM kernels, replacing the old AQT-based GemliteUIntXWeightOnlyConfig path. - UIntxBitPackedTensor: tensor subclass with from_hp(), dequantize(), and aten.linear/t/slice dispatch implementations - UIntxWeightOnlyConfig: weight-only quantization (4-bit/8-bit) - Int8DynamicActivationUIntxWeightConfig: int8 dynamic activation + uintx weight - Tests for both configs covering 4-bit, 8-bit, slice, and non-standard shapes ghstack-source-id: 5cdbbe1 Pull Request resolved: #4081
meta-cla
Bot
added
the
CLA Signed
jerryzh168
added
the
module: not user facing
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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):
Add v2 tensor subclass UIntxBitPackedTensor(TorchAOBaseTensor) using
gemlite bit-packing and Triton GEMM kernels, replacing the old AQT-based
GemliteUIntXWeightOnlyConfig path.
and aten.linear/t/slice dispatch implementations