-
Notifications
You must be signed in to change notification settings - Fork 551
Pull requests: pytorch/ao
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
float8: snapshot FSDP precomputed scale
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4555
opened Jul 3, 2026 by
nascheme
Loading…
kernel: synchronize autotuner cache updates
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4554
opened Jul 3, 2026 by
nascheme
Loading…
kernel: avoid partial Triton lazy initialization
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4553
opened Jul 3, 2026 by
nascheme
Loading…
optim: cache qmap values as tuples
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4552
opened Jul 3, 2026 by
nascheme
Loading…
Reuse direct grouped FP8 quantizers for blockwise MoE
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4551
opened Jul 2, 2026 by
iamzainhuda
Contributor
Loading…
HQQ general
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
skip failing CI tests
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
module: not user facing
Use this tag if you don't want this PR to show up in release notes
#4549
opened Jul 2, 2026 by
vkuzo
Contributor
Loading…
[Draft][xpu] Route per-block FP8 GEMM through torch._scaled_mm on XPU
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4548
opened Jul 2, 2026 by
hoshibara
Loading…
Add MoE blockwise FP8 DTensor and compile coverage
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
module: training
quantize_ api training flow
#4545
opened Jun 29, 2026 by
iamzainhuda
Contributor
Loading…
fix(_is_mslk_available): guard against missing CUDA/ROCm runtime
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
#4544
opened Jun 29, 2026 by
space192
Loading…
Fix constant_fold cleanup for shared get_attr targets
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4542
opened Jun 28, 2026 by
Kevin-Li-2025
•
Draft
Preserve nested control-flow subgraphs during pt2e convert
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4540
opened Jun 27, 2026 by
atharvjairath
Loading…
Add scale and zero-point dimension validation to quantization primitives
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4539
opened Jun 27, 2026 by
GiGiKoneti
Contributor
Loading…
Re-enable building under a free-threaded Python interpreter
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4537
opened Jun 26, 2026 by
nascheme
Loading…
[test] Refactor test_quant_api.py to use ToyLinearModel from torchao.…
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4536
opened Jun 25, 2026 by
willkn
Loading…
[XPU][CI] Add test/low_bit_optim.py to XPU CI
ciflow/xpu
label used to trigger xpu CI jobs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
xpu
Intel XPU related features
#4535
opened Jun 25, 2026 by
karol-brejna-i
•
Draft
[docs] Update static quantization tutorial to use Int8StaticActivationInt8WeightConfi issue fixed #3637
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
topic: documentation
Use this tag if this PR adds or improves documentation
#4533
opened Jun 24, 2026 by
Ali-Ch-001
Loading…
[xpu][mx][test] Enable multicard tests for xpu
ciflow/xpu
label used to trigger xpu CI jobs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
xpu
Intel XPU related features
[xpu][benchmarks] Enable microbenchmarks for Intel XPU
ciflow/xpu
label used to trigger xpu CI jobs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
module: inference
quantize_ api inference flow
test: skip int8/bf16 integration tests on pre-Ampere GPUs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4528
opened Jun 23, 2026 by
Suchitra-idu
Loading…
4 tasks done
test: skip semi-structured sparse test on pre-Ampere GPUs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#4527
opened Jun 23, 2026 by
Suchitra-idu
Loading…
1 of 2 tasks
[test][xpu] Add test_config.py, test_model_architecture.py and test_utils.py in Intel GPU CI
ciflow/xpu
label used to trigger xpu CI jobs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
xpu
Intel XPU related features
#4526
opened Jun 23, 2026 by
zxd1997066
Contributor
Loading…
Skip output observer when output qspec is None (weight-only PTQ)
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
meta-exported
#4525
opened Jun 22, 2026 by
ryan-monroe
Loading…
[xpu][benchmarks] Enable float8 roofline benchmarks for Intel XPU
benchmark
ciflow/xpu
label used to trigger xpu CI jobs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
module: inference
quantize_ api inference flow
module: training
quantize_ api training flow
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.