GitHub / pytorch/pytorch issues and pull requests
Labelled with: release notes: quantization
#153802 - [3/n][Optimus][Auto-AC] Support float8_e4m3fn quantization type and set scaling as the default
Pull Request -
State: open - Opened by mengluy0125 6 months ago
- 11 comments
Labels: fb-exported, Merged, Reverted, ciflow/trunk, release notes: quantization, module: inductor, ciflow/inductor, ci-no-td, release notes: inductor (aoti)
#153749 - Patch the _is_conv_node function
Pull Request -
State: closed - Opened by cccclai 6 months ago
- 11 comments
Labels: fb-exported, Merged, ciflow/trunk, release notes: quantization, release notes: AO frontend
#153749 - Patch the _is_conv_node function
Pull Request -
State: closed - Opened by cccclai 6 months ago
- 15 comments
Labels: fb-exported, Merged, Reverted, ciflow/trunk, release notes: quantization, release notes: AO frontend, ci-no-td
#153726 - [BE]: Type previously untyped decorators
Pull Request -
State: open - Opened by Skylion007 6 months ago
- 7 comments
Labels: module: typing, triaged, open source, better-engineering, Merged, Reverted, ciflow/trunk, release notes: quantization, release notes: python_frontend, ci-no-td
#153726 - [BE]: Type previously untyped decorators
Pull Request -
State: closed - Opened by Skylion007 6 months ago
- 3 comments
Labels: module: typing, triaged, open source, better-engineering, Merged, ciflow/trunk, release notes: quantization, release notes: python_frontend, merging
#153699 - Support boolean tensor for torch.fused_moving_avg_obs_fake_quant on CUDA
Pull Request -
State: open - Opened by Xia-Weiwen 6 months ago
- 1 comment
Labels: open source, release notes: quantization
#153613 - [Ez][BE] Make implicit subpackage explicit
Pull Request -
State: open - Opened by shink 6 months ago
- 7 comments
Labels: triaged, open source, release notes: quantization, module: inductor, release notes: AO frontend
#153601 - determine whether to round according to dtype
Pull Request -
State: open - Opened by shiyang-weng 6 months ago
- 1 comment
Labels: triaged, open source, release notes: quantization, fx, module: inductor, release notes: AO frontend
#153558 - Improve torch.ops typing
Pull Request -
State: closed - Opened by benjaminglass1 6 months ago
- 17 comments
Labels: open source, Merged, Reverted, ciflow/trunk, release notes: quantization, fx, module: inductor, ciflow/inductor, release notes: export, ci-no-td
#153558 - Improve torch.ops typing
Pull Request -
State: closed - Opened by benjaminglass1 6 months ago
- 18 comments
Labels: open source, Merged, Reverted, ciflow/trunk, release notes: quantization, fx, module: inductor, ciflow/inductor, release notes: export, ci-no-td
#153249 - [BE]: Update ruff to 0.11.8
Pull Request -
State: open - Opened by Skylion007 6 months ago
- 2 comments
Labels: oncall: distributed, open source, release notes: quantization, topic: not user facing, module: inductor, module: dynamo, ciflow/inductor
#153249 - [BE]: Update ruff to 0.11.8
Pull Request -
State: closed - Opened by Skylion007 6 months ago
- 6 comments
Labels: oncall: distributed, open source, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, module: inductor, module: dynamo, ciflow/inductor, merging
#153248 - [Refactor] Explicilty spell out the namespace for device() function
Pull Request -
State: closed - Opened by desertfire 6 months ago
- 9 comments
Labels: module: cpu, ciflow/trunk, release notes: quantization, merging
#153244 - [Ez][BE]: Ensure matplotlib remains optional dependency via fake_quantize
Pull Request -
State: closed - Opened by Skylion007 6 months ago
- 11 comments
Labels: open source, better-engineering, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, release notes: AO frontend, merging
#153163 - [Release/2.6] Remove --no-deps and --no-index flag when building pytorch in docker build
Pull Request -
State: closed - Opened by ethanwee1 6 months ago
- 2 comments
Labels: oncall: distributed, module: cpu, release notes: quantization, release notes: releng, module: inductor, module: dynamo
#153153 - Use 3.27 as the minimum CMake version
Pull Request -
State: closed - Opened by cyyever 6 months ago
- 36 comments
Labels: module: bc-breaking, module: cpu, triaged, open source, windows-triaged, Merged, Reverted, ciflow/binaries, ciflow/trunk, release notes: quantization, topic: bc breaking, topic: not user facing, ciflow/periodic, ciflow/binaries_wheel, ciflow/mps, module: inductor, ciflow/inductor, ciflow/rocm, ciflow/xpu, ci-no-td, ciflow/linux-aarch64, ciflow/s390, ciflow/win-arm64, ciflow/h100
#153007 - Remove redundant type aliases of _device_t for torch.Device (#152952)
Pull Request -
State: closed - Opened by sanjai-11 7 months ago
- 16 comments
Labels: oncall: distributed, module: cpu, triaged, module: mkldnn, open source, module: amp (automated mixed precision), Stale, release notes: quantization, topic: not user facing, module: inductor, module: dynamo, release notes: distributed (checkpoint), suppress-bc-linter, module: compiled autograd, release notes: inductor (aoti)
#153007 - Remove redundant type aliases of _device_t for torch.Device (#152952)
Pull Request -
State: open - Opened by sanjai-11 7 months ago
- 14 comments
Labels: oncall: distributed, module: cpu, triaged, module: mkldnn, open source, module: amp (automated mixed precision), release notes: quantization, topic: not user facing, module: inductor, module: dynamo, release notes: distributed (checkpoint), suppress-bc-linter, module: compiled autograd, release notes: inductor (aoti)
#152982 - [torch][ao] Properly strip tracking stats in _fold_conv_bn_qat for 1D
Pull Request -
State: closed - Opened by JakeStevens 7 months ago
- 14 comments
Labels: fb-exported, Merged, ciflow/trunk, release notes: quantization, release notes: AO frontend, merging
#152982 - [torch][ao] Properly strip tracking stats in _fold_conv_bn_qat for 1D
Pull Request -
State: open - Opened by JakeStevens 7 months ago
- 9 comments
Labels: fb-exported, ciflow/trunk, release notes: quantization, release notes: AO frontend
#152819 - [TEST][Quantization] Skip test_learnable due to hypothesis
Pull Request -
State: open - Opened by Aidyn-A 7 months ago
- 5 comments
Labels: triaged, open source, release notes: quantization, topic: not user facing
#152811 - [Quant][X86] add an op to compute uint8 batch norm 2d
Pull Request -
State: closed - Opened by Xia-Weiwen 7 months ago
- 3 comments
Labels: module: cpu, open source, Merged, ciflow/trunk, release notes: quantization, intel, merging
#152787 - Extract DeviceType to a standalone header file
Pull Request -
State: open - Opened by desertfire 7 months ago
- 14 comments
Labels: oncall: jit, module: cpu, module: mkldnn, ciflow/trunk, release notes: quantization, ciflow/inductor
#152787 - Extract DeviceType to a standalone header file
Pull Request -
State: closed - Opened by desertfire 7 months ago
- 16 comments
Labels: oncall: jit, module: cpu, module: mkldnn, ciflow/trunk, release notes: quantization, ciflow/inductor
#152619 - [DO NOT REVIEW] Implement __obj_flatten__ for LinearPackedParamsBase
Pull Request -
State: open - Opened by hl475 7 months ago
- 13 comments
Labels: module: cpu, fb-exported, ciflow/trunk, release notes: quantization
#152619 - [fbgemm] Implement __obj_flatten__ for LinearPackedParamsBase
Pull Request -
State: closed - Opened by hl475 7 months ago
- 19 comments
Labels: module: cpu, fb-exported, ciflow/trunk, release notes: quantization, merging
#152553 - [BE] Replace func_name with __func__
Pull Request -
State: closed - Opened by malfet 7 months ago
- 4 comments
Labels: module: cpu, fb-exported, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, merging
#152508 - [quantizer] Fix quantizer tests after dq conv is enabled
Pull Request -
State: open - Opened by mcr229 7 months ago
- 2 comments
Labels: fb-exported, ciflow/trunk, release notes: quantization, release notes: AO frontend
#152411 - [Quant][X86] add ops to compute uint8 pointwise add/add_relu
Pull Request -
State: closed - Opened by Xia-Weiwen 7 months ago
- 7 comments
Labels: module: cpu, open source, Merged, ciflow/trunk, release notes: quantization, intel, merging
#152237 - Fix broken URLs
Pull Request -
State: closed - Opened by shoumikhin 7 months ago
- 3 comments
Labels: oncall: distributed, oncall: jit, module: cpu, module: mkldnn, Merged, NNC, ciflow/trunk, release notes: quantization, release notes: releng, ciflow/mps, module: inductor, module: dynamo, ciflow/inductor, merging, ciflow/linux-aarch64
#151972 - [1/N] Deprecate c10::string_view and at::string
Pull Request -
State: closed - Opened by cyyever 7 months ago
- 10 comments
Labels: oncall: distributed, oncall: jit, module: cpu, triaged, open source, Merged, ciflow/binaries, ciflow/trunk, release notes: quantization, release notes: distributed (c10d), ciflow/periodic, ciflow/mps, ciflow/inductor, merging, release notes: inductor (aoti)
#151972 - [1/N] Deprecate c10::string_view and at::string
Pull Request -
State: closed - Opened by cyyever 7 months ago
- 10 comments
Labels: oncall: distributed, oncall: jit, module: cpu, triaged, open source, Merged, ciflow/binaries, ciflow/trunk, release notes: quantization, release notes: distributed (c10d), ciflow/periodic, ciflow/mps, ciflow/inductor, release notes: inductor (aoti)
#151888 - Fix xrefs
Pull Request -
State: closed - Opened by shoumikhin 7 months ago
- 3 comments
Labels: oncall: distributed, oncall: jit, release notes: quantization, fx, merging, release notes: distributed (torchelastic)
#151888 - Fix xrefs
Pull Request -
State: open - Opened by shoumikhin 7 months ago
- 1 comment
Labels: oncall: distributed, oncall: jit, release notes: quantization, fx, release notes: distributed (torchelastic)
#151434 - Implement fexp for avx2 and avx512
Pull Request -
State: closed - Opened by timocafe 7 months ago
- 2 comments
Labels: oncall: distributed, module: cpu, module: mkldnn, open source, module: amp (automated mixed precision), NNC, release notes: quantization, release notes: releng, module: inductor, module: dynamo, release notes: distributed (checkpoint), module: compiled autograd
#151292 - Remove outdated Android workarounds of nearbyintf
Pull Request -
State: open - Opened by cyyever 7 months ago
- 23 comments
Labels: module: cpu, triaged, open source, oncall: mobile, ciflow/trunk, release notes: quantization, ciflow/mps, test-config/executorch
#151241 - [BE][1/2] Move original_weights_lookup attribute to constant
Pull Request -
State: closed - Opened by bbeckca 7 months ago
- 7 comments
Labels: fb-exported, ciflow/trunk, release notes: quantization, fx, release notes: AO frontend, merging
#151191 - Fix DWConv in QNNPACK for aarch32
Pull Request -
State: closed - Opened by joseluisbf-kpsr 7 months ago
- 7 comments
Labels: module: cpu, triaged, open source, Stale, release notes: quantization
#151186 - autograd: Add VJP and JVP rules for aten::aminmax
Pull Request -
State: open - Opened by vijayabhaskar-ev 7 months ago
- 17 comments
Labels: oncall: distributed, module: cpu, triaged, module: mkldnn, open source, release notes: quantization, release notes: autograd, module: inductor, module: dynamo, release notes: distributed (checkpoint), module: compiled autograd, release notes: inductor (aoti)
#151070 - [2/N] Use internal linkage in aten C++ files
Pull Request -
State: closed - Opened by cyyever 7 months ago
- 8 comments
Labels: module: cpu, triaged, open source, oncall: mobile, Merged, ciflow/trunk, release notes: quantization, release notes: linalg_frontend, ciflow/periodic, ciflow/android, merging
#150930 - [1/N] Use internal linkage in torch/csrc C++ files.
Pull Request -
State: closed - Opened by cyyever 7 months ago
- 11 comments
Labels: oncall: distributed, module: cpu, module: mkldnn, open source, NNC, ciflow/trunk, release notes: quantization, release notes: linalg_frontend, ciflow/periodic, module: dynamo, ciflow/inductor, merging, ciflow/linux-aarch64
#150890 - [AO] fix per token block size calculation
Pull Request -
State: closed - Opened by mcr229 7 months ago
- 6 comments
Labels: Merged, ciflow/trunk, release notes: quantization, release notes: AO frontend, merging
#150831 - [Quant][PT2E][X86] Enable annotation of aten.mul.tensor with X86InductorQuantizer
Pull Request -
State: closed - Opened by Xia-Weiwen 8 months ago
- 3 comments
Labels: open source, release notes: quantization, intel
#150831 - [Quant][PT2E][X86] Enable annotation of aten.mul.tensor with X86InductorQuantizer
Pull Request -
State: open - Opened by Xia-Weiwen 8 months ago
- 1 comment
Labels: open source, release notes: quantization, intel
#150751 - [Quant][PT2E][X86] enable qconv1d-relu fusion
Pull Request -
State: open - Opened by Xia-Weiwen 8 months ago
- 4 comments
Labels: module: cpu, open source, ciflow/trunk, release notes: quantization, intel, module: inductor, ciflow/inductor, merging
#150751 - [Quant][PT2E][X86] enable qconv1d-relu fusion
Pull Request -
State: closed - Opened by Xia-Weiwen 8 months ago
- 7 comments
Labels: module: cpu, open source, Merged, ciflow/trunk, release notes: quantization, intel, module: inductor, ciflow/inductor, merging
#150644 - [AO] Refactor convert and add QuantAffinePlaceholderObserver
Pull Request -
State: open - Opened by mcr229 8 months ago
- 14 comments
Labels: ciflow/trunk, release notes: quantization
#150644 - [AO] Refactor convert and add QuantAffinePlaceholderObserver
Pull Request -
State: closed - Opened by mcr229 8 months ago
- 19 comments
Labels: Merged, ciflow/trunk, release notes: quantization, merging
#150643 - [AO] Add Moving Average Affine Observer
Pull Request -
State: open - Opened by mcr229 8 months ago
- 4 comments
Labels: release notes: quantization
#150642 - [AO] update port_metadata_pass to support quant_affine ops
Pull Request -
State: closed - Opened by mcr229 8 months ago
- 7 comments
Labels: Merged, release notes: quantization, release notes: AO frontend
#150642 - [AO] update port_metadata_pass to support quant_affine ops
Pull Request -
State: open - Opened by mcr229 8 months ago
- 4 comments
Labels: release notes: quantization, release notes: AO frontend
#150460 - [Cherry-pick] Make PyTorch buildable with cmake-4
Pull Request -
State: closed - Opened by malfet 8 months ago
- 1 comment
Labels: module: cpu, ciflow/binaries, release notes: quantization, release notes: releng
#150288 - [Intel GPU] Allow XPU backend in Quantize operators
Pull Request -
State: closed - Opened by yucai-intel 8 months ago
- 14 comments
Labels: open source, Merged, ciflow/trunk, release notes: quantization, merging
#150203 - [Cmake] Make PyTorch buildable by CMake-4.x
Pull Request -
State: closed - Opened by malfet 8 months ago
- 8 comments
Labels: module: cpu, Merged, release notes: quantization, release notes: build, topic: bug fixes, topic: build
#150203 - [Cmake] Make PyTorch buildable by CMake-4.x
Pull Request -
State: closed - Opened by malfet 8 months ago
- 3 comments
Labels: module: cpu, Merged, release notes: quantization, release notes: build, topic: bug fixes, topic: build, merging
#150116 - S390x: update more tests
Pull Request -
State: closed - Opened by AlekseiNikiforovIBM 8 months ago
- 7 comments
Labels: module: cpu, triaged, open source, Stale, ciflow/trunk, release notes: quantization, release notes: releng, fx, module: inductor, module: dynamo, ciflow/inductor, ciflow/s390
#150116 - S390x: update more tests
Pull Request -
State: open - Opened by AlekseiNikiforovIBM 8 months ago
- 4 comments
Labels: module: cpu, triaged, open source, ciflow/trunk, release notes: quantization, release notes: releng, fx, module: inductor, module: dynamo, ciflow/inductor, ciflow/s390
#150077 - Enable -Wunused on torch targets
Pull Request -
State: open - Opened by cyyever 8 months ago
- 2 comments
Labels: module: cpu, triaged, open source, release notes: quantization, topic: not user facing
#150077 - Enable -Wunused on torch targets
Pull Request -
State: closed - Opened by cyyever 8 months ago
- 19 comments
Labels: module: cpu, triaged, open source, Merged, Reverted, ciflow/binaries, ciflow/trunk, release notes: quantization, topic: not user facing, ciflow/periodic, merging, ci-no-td, skip-url-lint
#149958 - [inductor] Add typing to _inductor/ir.py
Pull Request -
State: open - Opened by rec 8 months ago
- 36 comments
Labels: oncall: distributed, module: rocm, module: cpu, open source, Merged, NNC, Reverted, ciflow/trunk, release notes: quantization, topic: not user facing, ciflow/mps, module: inductor, module: dynamo, ciflow/inductor, release notes: distributed (checkpoint), module: compiled autograd, ci-no-td, release notes: inductor (aoti), skip-url-lint
#149708 - [Quant][PT2E] add a lowering pass for x86 backend
Pull Request -
State: closed - Opened by Xia-Weiwen 8 months ago
- 5 comments
Labels: open source, Merged, ciflow/trunk, release notes: quantization, intel
#149595 - [Codemod][AddExplicitStrictExportForTrainingInferenceArg] caffe2/
Pull Request -
State: closed - Opened by gmagogsfm 8 months ago
- 16 comments
Labels: oncall: distributed, fb-exported, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, fx, module: inductor, ciflow/inductor, merging
#149595 - [Codemod][AddExplicitStrictExportForTrainingInferenceArg] caffe2/
Pull Request -
State: open - Opened by gmagogsfm 8 months ago
- 4 comments
Labels: oncall: distributed, fb-exported, ciflow/trunk, release notes: quantization, topic: not user facing, fx, module: inductor, ciflow/inductor
#149498 - Fix ValueError issue
Pull Request -
State: open - Opened by FlintWangacc 8 months ago
- 4 comments
Labels: module: cpu, open source, module: amp (automated mixed precision), release notes: quantization, module: dynamo
#149498 - Fix ValueError issue
Pull Request -
State: closed - Opened by FlintWangacc 8 months ago
- 4 comments
Labels: module: cpu, open source, module: amp (automated mixed precision), release notes: quantization, module: dynamo
#149435 - Enable fast path for qlinear (static/dynamic) and qadd for AArch64 though ACL directly.
Pull Request -
State: open - Opened by fadara01 8 months ago
- 5 comments
Labels: module: cpu, open source, module: arm, release notes: quantization, ciflow/linux-aarch64, arm priority
#149435 - Enable fast path for qlinear (static/dynamic) and qadd for AArch64 though ACL directly.
Pull Request -
State: closed - Opened by fadara01 8 months ago
- 9 comments
Labels: module: cpu, open source, module: arm, release notes: quantization, ciflow/linux-aarch64, arm priority
#149417 - [Build] Guard per-op headers in ACLUtils.cpp
Pull Request -
State: closed - Opened by malfet 8 months ago
- 5 comments
Labels: module: cpu, fb-exported, Merged, ciflow/trunk, release notes: quantization, merging
#149330 - [torch][ao] Do not crash numerics debugger if the shape of the tensors do not match
Pull Request -
State: open - Opened by dulinriley 8 months ago
- 15 comments
Labels: fb-exported, Stale, ciflow/trunk, release notes: quantization, release notes: AO frontend
#149268 - Fix mps scaled dot attention
Pull Request -
State: closed - Opened by rakshekaraj 8 months ago
- 6 comments
Labels: module: cpu, triaged, open source, module: amp (automated mixed precision), Stale, release notes: quantization, release notes: mps
#149257 - [BE]: Apply ruff PERF403 to use dict comprehensions more often
Pull Request -
State: open - Opened by Skylion007 8 months ago
- 6 comments
Labels: oncall: distributed, open source, better-engineering, Merged, Reverted, ciflow/trunk, release notes: quantization, release notes: releng, fx, module: inductor, ciflow/inductor, release notes: distributed (checkpoint), ci-no-td
#149235 - [export] specialize for aten.to
Pull Request -
State: closed - Opened by pianpwk 8 months ago
- 11 comments
Labels: oncall: distributed, fb-exported, Merged, ciflow/trunk, release notes: quantization, ciflow/inductor, merging, release notes: export
#149182 - Add test coverage
Pull Request -
State: closed - Opened by hl475 8 months ago
- 4 comments
Labels: fb-exported, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, fx, merging
#149171 - Update logic when producing key name for keep_original_weights
Pull Request -
State: closed - Opened by hl475 8 months ago
- 5 comments
Labels: fb-exported, Merged, ciflow/trunk, release notes: quantization, fx, release notes: AO frontend, merging
#149046 - Enable modernize-use-default-member-init and related fixes
Pull Request -
State: closed - Opened by cyyever 8 months ago
- 10 comments
Labels: module: cpu, triaged, module: mkldnn, open source, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, module: inductor, ciflow/inductor, ciflow/linux-aarch64
#149043 - [FIX] remove the duplicate key in DEFAULT_STATIC_QUANT_MODULE_MAPPINGS
Pull Request -
State: closed - Opened by hackty 8 months ago
- 8 comments
Labels: open source, Merged, ciflow/trunk, release notes: quantization, release notes: AO frontend, merging
#148996 - [codemod][lowrisk] Fix deprecated use of 0/NULL in caffe2/aten/src/ATen/native/quantized/cpu/qnnpack/src/fc-unpack.cc + 1
Pull Request -
State: closed - Opened by r-barnes 8 months ago
- 7 comments
Labels: module: cpu, fb-exported, Merged, ciflow/trunk, release notes: quantization, release notes: cpp, topic: improvements, topic: not user facing, merging
#148876 - Use device agnostic APIs and variable names for dtensor
Pull Request -
State: closed - Opened by amathewc 8 months ago
- 23 comments
Labels: oncall: distributed, module: cpu, triaged, module: mkldnn, open source, module: amp (automated mixed precision), NNC, release notes: quantization, topic: not user facing, module: inductor, module: dynamo, release notes: distributed (checkpoint), module: compiled autograd
#148791 - add `torch.float4_e2m1fn_x2` to PyTorch
Pull Request -
State: closed - Opened by vkuzo 9 months ago
- 9 comments
Labels: release notes: quantization
#148653 - Enable qint8 and quint8 add for AArch64 using ACL directly
Pull Request -
State: closed - Opened by fadara01 9 months ago
- 7 comments
Labels: module: cpu, open source, module: arm, Merged, release notes: quantization, merging, ciflow/linux-aarch64, arm priority
#148585 - Enable fast qlinear static/dynamic path for AArch64 through ACL directly
Pull Request -
State: closed - Opened by fadara01 9 months ago
- 8 comments
Labels: module: cpu, open source, module: arm, Merged, release notes: quantization, merging, ciflow/linux-aarch64, arm priority
#148583 - Enable fast qlinear static/dynamic path for AArch64 through ACL directly
Pull Request -
State: closed - Opened by fadara01 9 months ago
- 2 comments
Labels: module: cpu, open source, release notes: quantization
#148529 - Fix clang-tidy bugprone* warnings
Pull Request -
State: closed - Opened by cyyever 9 months ago
- 9 comments
Labels: oncall: distributed, module: cpu, triaged, open source, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, module: dynamo, ciflow/inductor, merging, module: compiled autograd, release notes: inductor (aoti)
#148529 - Fix clang-tidy bugprone* warnings
Pull Request -
State: closed - Opened by cyyever 9 months ago
- 9 comments
Labels: oncall: distributed, module: cpu, triaged, open source, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, module: dynamo, ciflow/inductor, module: compiled autograd, release notes: inductor (aoti)
#148380 - [1/n][Optimus][Auto-AC] Support activation quantization without scaling
Pull Request -
State: closed - Opened by mengluy0125 9 months ago
- 19 comments
Labels: fb-exported, ciflow/trunk, release notes: quantization, module: inductor, module: dynamo, ciflow/inductor, release notes: inductor, merging
#148380 - [1/n][Optimus][Auto-AC] Support activation quantization without scaling
Pull Request -
State: open - Opened by mengluy0125 9 months ago
- 17 comments
Labels: fb-exported, ciflow/trunk, release notes: quantization, module: inductor, module: dynamo, ciflow/inductor, release notes: inductor
#148346 - Symmetrization of Cholesky backward gradient
Pull Request -
State: closed - Opened by ayghri 9 months ago
- 3 comments
Labels: oncall: distributed, module: cpu, triaged, module: mkldnn, open source, module: amp (automated mixed precision), release notes: quantization, release notes: releng, module: inductor, module: dynamo, release notes: distributed (checkpoint)
#148190 - [BE][Ez]: Use itertools.chain.from_iterable when possible
Pull Request -
State: closed - Opened by Skylion007 9 months ago
- 3 comments
Labels: oncall: distributed, triaged, open source, better-engineering, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, fx, module: inductor, module: dynamo, ciflow/inductor, release notes: AO frontend, merging
#148185 - [BE][PYFMT] migrate PYFMT for `torch/ao/` to `ruff format`
Pull Request -
State: closed - Opened by XuehaiPan 9 months ago
- 4 comments
Labels: open source, better-engineering, Merged, ciflow/trunk, release notes: quantization, topic: not user facing
#148066 - use identity op for alpha=inf in torch.celu and quantized_celu
Pull Request -
State: open - Opened by redwrasse 9 months ago
- 2 comments
Labels: module: cpu, triaged, open source, Stale, release notes: quantization
#147770 - add pt2 testing for torch.float8_e8m0fnu
Pull Request -
State: closed - Opened by vkuzo 9 months ago
- 2 comments
Labels: Stale, release notes: quantization, fx
#147747 - Adding MVP of P1 INT16 Full
Pull Request -
State: closed - Opened by Ivan-Dimitrov 9 months ago
- 5 comments
Labels: fb-exported, Stale, release notes: quantization
#147747 - Adding MVP of P1 INT16 Full
Pull Request -
State: closed - Opened by Ivan-Dimitrov 9 months ago
- 5 comments
Labels: fb-exported, Stale, release notes: quantization
#147511 - Enable UBSAN test
Pull Request -
State: closed - Opened by cyyever 9 months ago
- 6 comments
Labels: triaged, open source, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, merging
#147501 - removed zero dim cpu logic from fake_tensor.py
Pull Request -
State: open - Opened by zero000064 9 months ago
- 31 comments
Labels: oncall: distributed, module: cpu, triaged, open source, module: amp (automated mixed precision), NNC, release notes: quantization, topic: not user facing, module: inductor, module: dynamo, release notes: distributed (checkpoint), module: compiled autograd
#147467 - not for land: just testing
Pull Request -
State: closed - Opened by vkuzo 9 months ago
- 1 comment
Labels: release notes: quantization, topic: not user facing
#147466 - add the `torch.float8_e8m0fnu` dtype to PyTorch
Pull Request -
State: closed - Opened by vkuzo 9 months ago
- 6 comments
Labels: module: cpu, Merged, ciflow/trunk, release notes: quantization, merging
#147462 - add the torch.float8_e8m0fnu` dtype to PyTorch
Pull Request -
State: closed - Opened by vkuzo 9 months ago
- 4 comments
Labels: module: cpu, ciflow/trunk, release notes: quantization
#147447 - [Export][AO] Include another batch_norm op in supported batch_norms
Pull Request -
State: closed - Opened by anzr299 9 months ago
- 2 comments
Labels: open source, release notes: quantization, release notes: AO frontend
#147406 - fix pt2e block wise quantization unit test
Pull Request -
State: closed - Opened by cccclai 9 months ago
- 4 comments
Labels: fb-exported, Merged, ciflow/trunk, release notes: quantization, topic: not user facing, merging