Commits

Branch selector

 v0.1.48

User selector

All users

Datepicker

All time

Commit History

Commits on May 8, 2023

• Merge branch 'main' of github.com:abetlen/llama_cpp_python into main

  abetlen

  committed
  7af1f4c

  Copy full SHA for 7af1f4c

• Bump version

  abetlen

  committed
  c37883b

  Copy full SHA for c37883b

• Fix: default repeat_penalty

  abetlen

  committed
  82d138f

  Copy full SHA for 82d138f

• Merge pull request #153 from SagsMug/main

  Show description for ed0f48b
  abetlen

  authored
  ed0f48b

  Copy full SHA for ed0f48b

• Bump version

  abetlen

  committed
  a3cc7bf

  Copy full SHA for a3cc7bf

• Bugfix: not falling back to environment variables when default is value is set.

  abetlen

  committed
  29f094b

  Copy full SHA for 29f094b

• Bump version

  abetlen

  committed
  6d69461

  Copy full SHA for 6d69461

• Show default value when --help is called

  abetlen

  committed
  0d6c600

  Copy full SHA for 0d6c600

• Use environment variable if parsed cli arg is None

  abetlen

  committed
  022e9eb

  Copy full SHA for 022e9eb

• Fix lora

  SagsMug

  committed
  eaf9f19

  Copy full SHA for eaf9f19

• Fix session loading and saving in low level example chat

  SagsMug

  committed
  2c0d9b1

  Copy full SHA for 2c0d9b1

• Merge branch 'main' of https://github.com/abetlen/llama-cpp-python

  SagsMug

  committed
  ed66a46

  Copy full SHA for ed66a46

• Set repeat_penalty to 0 by default

  abetlen

  committed
  0d751a6

  Copy full SHA for 0d751a6

• Add openai frequency and presence penalty parameters. Closes #169

  abetlen

  committed
  65d9cc0

  Copy full SHA for 65d9cc0

• Bump version

  abetlen

  committed
  75d8619

  Copy full SHA for 75d8619

• Bugfix for models endpoint

  abetlen

  committed
  a0b61ea

  Copy full SHA for a0b61ea

• Change pointer to lower overhead byref

  abetlen

  committed
  e72f586

  Copy full SHA for e72f586

Commits on May 7, 2023

• Added cache size to settins object.

  abetlen

  committed
  14da46f

  Copy full SHA for 14da46f

• Add in-memory longest prefix cache. Closes #158

  abetlen

  committed
  0e94a70

  Copy full SHA for 0e94a70

• Fix return type

  abetlen

  committed
  8dfde63

  Copy full SHA for 8dfde63

• Format

  abetlen

  committed
  2753b85

  Copy full SHA for 2753b85

• Update README

  abetlen

  committed
  4f8cf52

  Copy full SHA for 4f8cf52

• Update README to use cli options for server

  abetlen

  committed
  3adc8fb

  Copy full SHA for 3adc8fb

• Add verbose flag to server

  abetlen

  committed
  627811e

  Copy full SHA for 627811e

• Bump version

  abetlen

  committed
  5f43c55

  Copy full SHA for 5f43c55

• Fix mlock_supported and mmap_supported return type

  abetlen

  committed
  3fbda71

  Copy full SHA for 3fbda71

• Update cpu_count

  abetlen

  committed
  5a3413e

  Copy full SHA for 5a3413e

• Update settings fields and defaults

  abetlen

  committed
  1a00e45

  Copy full SHA for 1a00e45

• Revert "llama_cpp server: delete some ignored / unused parameters"

  Show description for 8675397
  abetlen

  committed
  8675397

  Copy full SHA for 8675397

• Revert "llama_cpp server: mark model as required"

  Show description for c382d8f
  abetlen

  committed
  c382d8f

  Copy full SHA for c382d8f

• Merge branch 'main' of github.com:abetlen/llama_cpp_python into better-server-params-and-fields

  abetlen

  committed
  d8fddcc

  Copy full SHA for d8fddcc

• Update README

  abetlen

  committed
  397ae97

  Copy full SHA for 397ae97

• Merge branch 'main' of github.com:abetlen/llama_cpp_python into main

  abetlen

  committed
  1c18845

  Copy full SHA for 1c18845

• Update llama.cpp

  abetlen

  committed
  7c3743f

  Copy full SHA for 7c3743f

• Update issue templates

  abetlen

  authored
  c76e091

  Copy full SHA for c76e091

Pagination

Previous

Next