Commits

Branch selector

 assert-restore-abort

User selector

All users

Datepicker

All time

Commit History

Commits on Nov 28, 2023

• ggml : restore abort() in GGML_ASSERT

  cebtenzzre

  committed
  bb39b87

  Copy full SHA for bb39b87

Commits on Nov 27, 2023

• cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)

  Show description for b38a16d
  bandoti

  authored
  b38a16d

  Copy full SHA for b38a16d

• readme : add Amica to UI list (#4230)

  kasumi-1

  authored
  0dab8cd

  Copy full SHA for 0dab8cd

• examples : iOS example with swift ui (#4159)

  Show description for bb03290
  

  bachittle

  and

  ggerganov

  authored
  bb03290

  Copy full SHA for bb03290

• ggml : fix -Warray-bounds warning with gcc (#4231)

  cebtenzzre

  authored
  f3b2698

  Copy full SHA for f3b2698

Commits on Nov 26, 2023

• lookahead : support `-n -1` infinite generation

  ggerganov

  committed
  3e73d31

  Copy full SHA for 3e73d31

• readme : update hot topics

  ggerganov

  authored
  9656026

  Copy full SHA for 9656026

• lookahead : add example for lookahead decoding (#4207)

  Show description for 922754a
  

  ggerganov

  and

  slaren

  authored
  922754a

  Copy full SHA for 922754a

• metal : fix yarn (#4220)

  Show description for 22da055
  jxy

  authored
  22da055

  Copy full SHA for 22da055

Commits on Nov 25, 2023

• scripts : Use mmap in torch load (#4202)

  Show description for 1ddb52e
  Galunid

  authored
  1ddb52e

  Copy full SHA for 1ddb52e

• llama : grammar `reserve` space in `decode_utf8` (#4210)

  Show description for f837c3a
  MarcusDunn

  authored
  f837c3a

  Copy full SHA for f837c3a

• Update docs for yarn_ext_factor <0.0 as unspecified instead of NaN (#4189)

  crasm

  authored
  3014b54

  Copy full SHA for 3014b54

• readme : update hot topics

  ggerganov

  authored
  04814e7

  Copy full SHA for 04814e7

• server : OAI API compatibility (#4198)

  Show description for af19d35
  

  3 peopleauthored
  af19d35

  Copy full SHA for af19d35

Commits on Nov 24, 2023

• llama : set metal log callback correctly (#4204)

  slaren

  authored
  e9c13ff

  Copy full SHA for e9c13ff

• ggml-cuda : support stablelm rope (#4156)

  Show description for 8a052c1
  

  slaren

  and

  ggerganov

  authored
  8a052c1

  Copy full SHA for 8a052c1

• convert : fix tensors using grad in some models (#4173)

  Galunid

  authored
  189d684

  Copy full SHA for 189d684

• main.swift : fix eos checking (#4197)

  Show description for 2568a4b
  eastriverlee

  authored
  2568a4b

  Copy full SHA for 2568a4b

• readme : use PATH for Windows ROCm (#4195)

  Show description for b35f3d0
  jammm

  authored
  b35f3d0

  Copy full SHA for b35f3d0

Commits on Nov 23, 2023

• Fix incorrect format strings and uninitialized variables. (#4133)

  Show description for 55978ce
  haohui

  authored
  55978ce

  Copy full SHA for 55978ce

• llama : KV cache view API + better KV cache management (#4170)

  Show description for 6b0a742
  

  ggerganov

  and

  KerfuffleV2

  authored
  6b0a742

  Copy full SHA for 6b0a742

• readme : update hot topics

  ggerganov

  authored
  d103d93

  Copy full SHA for d103d93

• examples : fix typo in parallel example doc comment (#4181)

  Show description for 9d5949f
  danbev

  authored
  9d5949f

  Copy full SHA for 9d5949f

• docs : add llama-star arch idea

  ggerganov

  committed
  ff8238f

  Copy full SHA for ff8238f

Commits on Nov 21, 2023

• stablelm : simplify + speedup generation (#4153)

  Galunid

  authored
  8e672ef

  Copy full SHA for 8e672ef

Commits on Nov 20, 2023

• finetune - update readme to mention llama support only (#4148)

  Galunid

  authored
  0b871f1

  Copy full SHA for 0b871f1

• readme : update ROCm Windows instructions (#4122)

  Show description for dfc7cd4
  

  jammm

  and

  cebtenzzre

  authored
  dfc7cd4

  Copy full SHA for dfc7cd4

• main : Add ChatML functionality to main example (#4046)

  Show description for 881800d
  Sebby37

  authored
  881800d

  Copy full SHA for 881800d

• ci : add flake8 to github actions (python linting) (#4129)

  Show description for f23c035
  Galunid

  authored
  f23c035

  Copy full SHA for f23c035

• speculative : fix prompt tokenization in speculative example (#4025)

  Show description for 40a34fe
  AutonomicPerfectionist

  authored
  40a34fe

  Copy full SHA for 40a34fe

Commits on Nov 19, 2023

• Revert "finetune : add --n-gpu-layers flag info to --help (#4128)"

  Show description for dae06c0
  ggerganov

  committed
  dae06c0

  Copy full SHA for dae06c0

• finetune : add --n-gpu-layers flag info to --help (#4128)

  csaben

  authored
  05e8301

  Copy full SHA for 05e8301

• server : relay error messages (#4131)

  SoftwareRenderer

  authored
  936c79b

  Copy full SHA for 936c79b

• common : comma should be semicolon (#4137)

  kchro3

  authored
  262005a

  Copy full SHA for 262005a

• gitignore : tokenize

  ggerganov

  committed
  35985ac

  Copy full SHA for 35985ac

Pagination

Previous

Next