Commits

Branch selector

 emu

User selector

vkuzo

Datepicker

All time

Commit History

Commits on Sep 1, 2023

• dynamo: trace autograd.Function with tensor subclass input (pytorch#108093)

  Show description for 3702980
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  3702980

  Copy full SHA for 3702980

Commits on Aug 23, 2023

• pt2: make aot_eager backend handle basic float8 operations (pytorch#107783)

  Show description for 61fe49b
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  61fe49b

  Copy full SHA for 61fe49b

Commits on Aug 22, 2023

• pt2: make aot_eager backend handle basic float8 operations (pytorch#107642)

  Show description for 24147a8
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  24147a8

  Copy full SHA for 24147a8

Commits on Jul 25, 2023

• add basic cuda support for float8 dtypes (pytorch#105807)

  Show description for 8b34fa5
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  8b34fa5

  Copy full SHA for 8b34fa5

Commits on Apr 18, 2023

• torch._int_mm: fix triton kernel caching (pytorch#99283)

  Show description for 5ff2ad6
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  5ff2ad6

  Copy full SHA for 5ff2ad6

Commits on Mar 10, 2023

• pt2e short term quant: respect qmin/qmax for linear weight (pytorch#96232)

  Show description for cdab1d6
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  cdab1d6

  Copy full SHA for cdab1d6

Commits on Mar 4, 2023

• Add various uninterpreted bit tensor data types (try 2) (pytorch#95860)

  Show description for dc70e81
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  dc70e81

  Copy full SHA for dc70e81

Commits on Feb 18, 2023

• Add various uninterpreted bit tensor data types (pytorch#94992)

  Show description for 9dbfca7
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  9dbfca7

  Copy full SHA for 9dbfca7

Commits on Feb 13, 2023

• ao migration: remove package test as this behavior is tested by other things (pytorch#94422)

  Show description for 216f88d
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  216f88d

  Copy full SHA for 216f88d

• ao migration: delete unused test class (pytorch#94420)

  Show description for f6adbf4
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  f6adbf4

  Copy full SHA for f6adbf4

Commits on Feb 9, 2023

• ao migration: fix broken import, try 2 (pytorch#94458)

  Show description for c1e2704
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  c1e2704

  Copy full SHA for c1e2704

Commits on Feb 7, 2023

• AO migration: replace torch internal callsites (pytorch#94170)

  Show description for f15ab8a
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  f15ab8a

  Copy full SHA for f15ab8a

• AO migration: migrate .rst files to new locations (pytorch#94211)

  Show description for a9f57db
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  a9f57db

  Copy full SHA for a9f57db

Commits on Feb 3, 2023

• ns: add compare_weights API with a single model (pytorch#92058)

  Show description for f84f89b
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  f84f89b

  Copy full SHA for f84f89b

• add add_loggers implementation using PNP (pytorch#91639)

  Show description for 660bea1
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  660bea1

  Copy full SHA for 660bea1

Commits on Feb 1, 2023

• pnp: move shadow loggers to parent module (pytorch#91428)

  Show description for 6fe234e
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  6fe234e

  Copy full SHA for 6fe234e

• ns: change PNP testing to use QNNPACK (pytorch#91421)

  Show description for 56f9475
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  56f9475

  Copy full SHA for 56f9475

Commits on Jan 4, 2023

• quant: make various configs printable (pytorch#91419)

  Show description for ebb7f20
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  ebb7f20

  Copy full SHA for ebb7f20

Commits on Dec 15, 2022

• add autocast keys to pybind11 DispatchKey object (pytorch#90821)

  Show description for d19791e
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  d19791e

  Copy full SHA for d19791e

Commits on Nov 24, 2022

• quantization: deprecate observer compute_dtype and replace with is_dynamic (pytorch#85431)

  Show description for 22a1b5e
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  22a1b5e

  Copy full SHA for 22a1b5e

Commits on Oct 31, 2022

• make autocast cache global instead of thread-local (pytorch#86492)

  Show description for 75dbe37
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  75dbe37

  Copy full SHA for 75dbe37

Commits on Oct 6, 2022

• PNP: early FX numeric suite tool to quantize each layer N times (pytorch#80521)

  Show description for 237316a
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  237316a

  Copy full SHA for 237316a

Commits on Oct 3, 2022

• remove vkuzo from CODEOWNERS for AO (pytorch#86038)

  Show description for 4a528bc
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  4a528bc

  Copy full SHA for 4a528bc

Commits on Sep 26, 2022

• fix segmentation fault in QTensor.choose_qparams_optimized (pytorch#85552)

  Show description for a8ca0d4
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  a8ca0d4

  Copy full SHA for a8ca0d4

Commits on Sep 21, 2022

• quantization: align observer dtype with reference model spec (pytorch#85345)

  Show description for 0996595
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  0996595

  Copy full SHA for 0996595

Commits on Sep 20, 2022

• fx quant: fix bug in custom module test (pytorch#85344)

  Show description for cb8e73b
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  cb8e73b

  Copy full SHA for cb8e73b

Commits on Sep 9, 2022

• quant: add extra_repr to HistogramObserver (pytorch#84760)

  Show description for 1dabb51
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  1dabb51

  Copy full SHA for 1dabb51

Commits on Aug 23, 2022

• Remove DBR quantization from the codebase (pytorch#83642)

  Show description for 58170fb
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  58170fb

  Copy full SHA for 58170fb

Commits on Jul 6, 2022

• fx quant: fix warning in util function when cloning tensors (pytorch#80883)

  Show description for ce0786a
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  ce0786a

  Copy full SHA for ce0786a

Commits on Jun 17, 2022

• fx quant: refactor qconfig setting out of find_matches

  Show description for 7b4e92a
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  7b4e92a

  Copy full SHA for 7b4e92a

Commits on Jun 16, 2022

• fx quant: unbreak Mac OS tests when MKLDNN is available

  Show description for 91c5fc3
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  91c5fc3

  Copy full SHA for 91c5fc3

Commits on Jun 8, 2022

• ns for fx: further fixes for kwargs-only

  Show description for d4aa204
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  d4aa204

  Copy full SHA for d4aa204

Commits on Jun 6, 2022

• quantization: remove most fp16 configs from fbgemm/qnnpack

  Show description for 71e1992
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  71e1992

  Copy full SHA for 71e1992

Commits on May 25, 2022

• ns for fx: remove restriction on nodes with no args and only kwargs

  Show description for 53e05ad
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  53e05ad

  Copy full SHA for 53e05ad

Commits on May 18, 2022

• quant doc: improve rendered documentation for backend_config_dict

  Show description for c15fca1
  

  vkuzo

  authored and

  pytorchmergebot

  committed
  c15fca1

  Copy full SHA for c15fca1

Pagination

Previous

Next