Skip to content

Pull requests: pytorch/ao

New pull request New
118 Open 1,576 Closed
118 Open 1,576 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

metal lowbit kernels: qmv_fast optimization CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2167 opened May 3, 2025 by manuelcandales Loading…
1
Update utils_parallel_dequant.cuh CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2164 opened May 2, 2025 by metascroy Loading…
1
[testing][do not land] Specify rocm runner for wheel build ciflow/rocm CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: rocm topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2161 opened May 1, 2025 by petrex Loading…
2
Remove fix not needed anymore after moving CUTLASS pin to v3.9.0 CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2160 opened May 1, 2025 by alexsamardzic Loading…
1
Implement dtensor.shard_dim_alltoall, aten.contiguous, aten.chunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2154 opened May 1, 2025 by nathan-az Loading…
1
8
[WIP]: Reduce torchao import time CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2153 opened Apr 30, 2025 by msaroufim Loading…
1
Generate speedup for inference CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: for developers Use this tag if this PR is mainly developer facing
#2151 opened Apr 30, 2025 by jainapurva Loading…
3
Remove preserve_zero and zero_point_domain from choose_qparams_affine CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: for developers Use this tag if this PR is mainly developer facing topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2149 opened Apr 29, 2025 by jainapurva • Draft
13
Support INT8 SDPA template for CPU CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2148 opened Apr 29, 2025 by Valentine233 Loading…
9
[WIP] all-gather fp8 for rowwise CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2145 opened Apr 28, 2025 by danielvegamyhre • Draft
1
[PT2E][X86] Migrate fusion passes in Inductor to torchao CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: new feature Use this tag if this PR adds a new feature
#2140 opened Apr 28, 2025 by Xia-Weiwen Loading…
18
Arm_inductor_quantizer for Pt2e quantization CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2139 opened Apr 28, 2025 by choudhary-devang Loading…
3
Add subclass based method for inference w/ MXFP8 CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. quantize topic: new feature Use this tag if this PR adds a new feature
#2132 opened Apr 25, 2025 by drisspg Loading…
5
[CPU] enable int8_dynamic_activation_int4_weight with Int4CPULayout CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. cpu quantize topic: new feature Use this tag if this PR adds a new feature
#2128 opened Apr 25, 2025 by Xia-Weiwen Loading…
3
Fix cuda compile error with bf16 CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported
#2122 opened Apr 24, 2025 by metascroy Loading…
9
Add pct_achievable_gemm_tops and pct_achievable_mem_bw to fp8 roofline utils benchmark CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: improvement Use this tag if this PR is an improvement (doesn't fit into any of the other categories)
#2120 opened Apr 23, 2025 by mreso Loading…
1
[not for landing/review] add fake quant ops for embedding/linear CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2110 opened Apr 23, 2025 by metascroy Loading…
1
Update sam2_base.py CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2108 opened Apr 22, 2025 by jlbmorales Loading…
2
Support microbenchmarking for low precision training CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: for developers Use this tag if this PR is mainly developer facing topic: performance Use this tag if this PR improves the performance of a feature
#2101 opened Apr 22, 2025 by jainapurva • Draft
2
Enhance test_autoquant_compile to support ROCm ciflow/rocm CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: rocm topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2100 opened Apr 22, 2025 by petrex Loading…
4
compare prepared vs. converted outputs for Embedding CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2087 opened Apr 21, 2025 by navsud Loading…
5
#1920 activation sparsity + compression CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2076 opened Apr 18, 2025 by ved1beta Loading…
5 tasks done
2
Enable InputRecorder to run in offline mode and cuda device CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported topic: not user facing Use this tag if you don't want this PR to show up in release notes
#2067 opened Apr 17, 2025 by danachang Loading…
12
ROCm mx-fp8 Gemm ciflow/rocm CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: rocm mx topic: new feature Use this tag if this PR adds a new feature
#2066 opened Apr 16, 2025 by petrex Loading…
1
Remove preserve_zero and zero_point_domain from choose_qparams_affine CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: improvement Use this tag if this PR is an improvement (doesn't fit into any of the other categories)
#2052 opened Apr 14, 2025 by jainapurva • Draft
1
ProTip! What’s not been updated in a month: updated:<2025-04-03.