Commits

Breadcrumbs

History for

onmain

User selector

All users

Datepicker

All time

Commit History

Commits on Mar 8, 2022

• remove output needs to requantized assertion

  Show description for 814ec8c
  

  jiyuanzFB

  authored and

  facebook-github-bot

  committed
  814ec8c

Commits on Mar 1, 2022

• fix handling nullptr rowOffsetBuf (pytorch#956)

  Show description for 389f89d
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  389f89d

• handling empty matrix in transpose (pytorch#955)

  Show description for 85ff0ff
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  85ff0ff

Commits on Feb 23, 2022

• disable direct conv path

  Show description for c2d46af
  

  jiyuanzFB

  authored and

  facebook-github-bot

  committed
  c2d46af

Commits on Feb 15, 2022

• use int64_t in fbgemmPartition1D (pytorch#933)

  Show description for f7050c9
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  f7050c9

Commits on Feb 8, 2022

• add direct conv to fbgemm (pytorch#901)

  Show description for f0f6ca7
  

  jiyuanzFB

  authored and

  facebook-github-bot

  committed
  f0f6ca7

Commits on Feb 5, 2022

• use thread local code cache in cpu quantized emb fwd (pytorch#903)

  Show description for e779169
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  e779169

Commits on Jan 21, 2022

• Transposed Direct Convolution for kh=2 kw=6

  Show description for 81719d6
  

  jiyuanzFB

  authored and

  facebook-github-bot

  committed
  81719d6

Commits on Jan 20, 2022

• enable -Wall -Wextra -Werror (pytorch#868)

  Show description for b047231
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  b047231

Commits on Jan 18, 2022

• remove extra ; after marco (pytorch#866)

  Show description for 80e3f16
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  80e3f16

• actually clamp denorm in RoundToFloat16 when clamp_denorms is set (pytorch#871)

  Show description for c3ad33c
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  c3ad33c

Commits on Jan 13, 2022

• conv code refactoring (pytorch#856)

  Show description for 3fac636
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  3fac636

• Disable clang inline asm workaround for clang-14 and later (pytorch#861)

  Show description for 135412d
  

  MatzeB

  authored and

  facebook-github-bot

  committed
  135412d

Commits on Jan 12, 2022

• Fix OSS license (pytorch#858)

  Show description for 9d7c48a
  

  jianyuh

  authored and

  facebook-github-bot

  committed
  9d7c48a

Commits on Jan 10, 2022

• Update OSS license (pytorch#855)

  Show description for 22d234e
  

  jianyuh

  authored and

  facebook-github-bot

  committed
  22d234e

Commits on Jan 8, 2022

• scale_bias_last option to support TBE layout (pytorch#848)

  Show description for 747fc4a
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  747fc4a

Commits on Dec 18, 2021

• Direct Convolution JIT assembly for KH=2, KW = 6

  Show description for 2ffb487
  

  jiyuanzFB

  authored and

  facebook-github-bot

  committed
  2ffb487

Commits on Dec 11, 2021

• Apply clang format to fbgemm (gpu) (pytorch#799)

  Show description for b9e66ca
  

  jianyuh

  authored and

  facebook-github-bot

  committed
  b9e66ca

Commits on Nov 30, 2021

• remove assumption number of rows is in 32 bit (#69066)

  Show description for ae24ea0
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  ae24ea0

Commits on Oct 15, 2021

• Remove dead includes in deeplearning/fbgemm/src

  Show description for 1c41a00
  

  Dead Code Bot

  authored and

  facebook-github-bot

  committed
  1c41a00

Commits on Oct 14, 2021

• Improve im2col for certain cases (pytorch#715)

  Show description for 0375f13
  

  dskhudia

  authored and

  facebook-github-bot

  committed
  0375f13

Commits on Oct 12, 2021

• Fix intermittant UBSAN error

  Show description for 9698cad
  

  dskhudia

  authored and

  facebook-github-bot

  committed
  9698cad

Commits on Sep 17, 2021

• Manually cache block attributes in PackBMatrix::pack_unpack_ (pytorch#702)

  Show description for dccc573
  

  swolchok

  authored and

  facebook-github-bot

  committed
  dccc573

Commits on Sep 16, 2021

• remove pendatic to avoid compile error (pytorch#701)

  Show description for 91fc122
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  91fc122

Commits on Sep 13, 2021

• call proper sparse_adagrad_ref on non-AVX2/512 machines (pytorch#693)

  Show description for 742ec0e
  

  shintaro-iwasaki

  authored and

  facebook-github-bot

  committed
  742ec0e

Commits on Aug 26, 2021

• Use F14Map instead of std::map in CodeCache.h, and reuse Ctile buffer in ExecuteU8S8.cc (pytorch#670)

  Show description for d5e66bf
  

  Andrew Tulloch

  authored and

  facebook-github-bot

  committed
  d5e66bf

Commits on Aug 9, 2021

• Fix an issue in the Avx2 code of sparse matrix multiply (pytorch#664)

  Show description for a35fa9f
  

  Ramesh Peri

  authored and

  facebook-github-bot

  committed
  a35fa9f

Commits on Aug 3, 2021

• Small commit to force a PyTorch submodule update PR (pytorch#659)

  Show description for 10ec0d3
  

  dskhudia

  authored and

  facebook-github-bot

  committed
  10ec0d3

• Improve performance of sparse fp32 GEMMs (pytorch#657)

  Show description for cbf1166
  

  Ramesh Peri

  authored and

  facebook-github-bot

  committed
  cbf1166

Commits on Jul 1, 2021

• Wextra pedantic fbgemm's (pytorch#642)

  Show description for 31905d2
  

  r-barnes

  authored and

  facebook-github-bot

  committed
  31905d2

Commits on Jun 17, 2021

• Deprecate old quanzation / dequantization util functions. (pytorch#630)

  Show description for 1bad64b
  

  caogao

  authored and

  facebook-github-bot

  committed
  1bad64b

Commits on Jun 10, 2021

• Add quantize and dequantize functions between rowwise-quantized int8 + fp32 scale/bias and fp32 embeddings. (pytorch#623)

  Show description for 3182125
  

  caogao

  authored and

  facebook-github-bot

  committed
  3182125

Commits on Jun 8, 2021

• fix build with gcc 5.4 (pytorch#622)

  Show description for 8aaefde
  

  dskhudia

  authored and

  facebook-github-bot

  committed
  8aaefde

• fix gconv + acc16 (#59541)

  Show description for 70a4042
  

  jspark1105

  authored and

  facebook-github-bot

  committed
  70a4042

Commits on Jun 7, 2021

• Unroll outer loop to improve performance (pytorch#617)

  Show description for baeb9a4
  

  dskhudia

  authored and

  facebook-github-bot

  committed
  baeb9a4

Pagination

PreviousNext