Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Sep 20, 2023

• Update llama_types and names to match openai api

  abetlen

  committed
  dbca136

  Copy full SHA for dbca136

• Update llama.cpp

  abetlen

  committed
  15000fc

  Copy full SHA for 15000fc

• Ignore version if set by pyenv

  abetlen

  committed
  0b2464c

  Copy full SHA for 0b2464c

Commits on Sep 18, 2023

• Update CHANGELOG

  abetlen

  committed
  3afbf2e

  Copy full SHA for 3afbf2e

• Update CHANGELOG

  abetlen

  committed
  6e167a2

  Copy full SHA for 6e167a2

• Update llama.cpp

  abetlen

  committed
  38e34c9

  Copy full SHA for 38e34c9

Commits on Sep 16, 2023

• Install required runtime dlls to package directory on windows

  abetlen

  committed
  8d75016

  Copy full SHA for 8d75016

Commits on Sep 15, 2023

• Bump version

  abetlen

  committed
  acf18fc

  Copy full SHA for acf18fc

• Update llama.cpp

  abetlen

  committed
  c7f45a7

  Copy full SHA for c7f45a7

• Remove confusing helpstring from server cli args. Closes #719

  abetlen

  committed
  b047b30

  Copy full SHA for b047b30

Commits on Sep 14, 2023

• Bump version

  abetlen

  committed
  24fec0b

  Copy full SHA for 24fec0b

• Fix issue installing on m1 macs

  abetlen

  committed
  dbd3a6d

  Copy full SHA for dbd3a6d

• Revert "Update llama.cpp"

  Show description for 482ecd7
  abetlen

  committed
  482ecd7

  Copy full SHA for 482ecd7

• Update llama.cpp

  abetlen

  committed
  f73e385

  Copy full SHA for f73e385

• Revert "Update llama.cpp"

  Show description for ca4eb95
  abetlen

  committed
  ca4eb95

  Copy full SHA for ca4eb95

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

  abetlen

  committed
  7da8e0f

  Copy full SHA for 7da8e0f

• Update base_path to fix issue resolving dll in windows isolation container.

  abetlen

  committed
  8474665

  Copy full SHA for 8474665

• Update examples from ggml to gguf and add hw-accel note for Web Server (#688)

  Show description for 40b2290
  

  jasonacox

  and

  abetlen

  authored
  40b2290

  Copy full SHA for 40b2290

• Update llama.cpp

  abetlen

  committed
  aa2f8a5

  Copy full SHA for aa2f8a5

• Fix dockerfiles to install starlette-context

  abetlen

  committed
  2291798

  Copy full SHA for 2291798

• Enable make fallback for scikit-build-core

  abetlen

  committed
  65a2a20

  Copy full SHA for 65a2a20

• Add documentation and changelog links in pyproject

  abetlen

  committed
  255d653

  Copy full SHA for 255d653

• Upgrade pip for editable installs

  abetlen

  committed
  95d5480

  Copy full SHA for 95d5480

• Bump version

  abetlen

  committed
  507bcc7

  Copy full SHA for 507bcc7

• Update CHANGELOG

  abetlen

  committed
  3e2250a

  Copy full SHA for 3e2250a

• Update CHANGELOG

  abetlen

  committed
  60119db

  Copy full SHA for 60119db

• Fix boolean env vars and cli arguments

  abetlen

  committed
  0449d29

  Copy full SHA for 0449d29

• Update app.py (#705)

  earonesty

  authored
  58a6e42

  Copy full SHA for 58a6e42

• Add numa support, low level api users must now explicitly call llama_backend_init at the start of their programs.

  abetlen

  committed
  f4090a0

  Copy full SHA for f4090a0

• Fix boolean cli flags

  abetlen

  committed
  c999325

  Copy full SHA for c999325

• Update CHANGELOG

  abetlen

  committed
  83764c5

  Copy full SHA for 83764c5

• Format

  abetlen

  committed
  4daf77e

  Copy full SHA for 4daf77e

• Update server params. Added lora_base, lora_path, low_vram, and main_gpu. Removed rms_norm_eps and n_gqa (deprecated in llama.cpp)

  abetlen

  committed
  2920c4b

  Copy full SHA for 2920c4b

• Reorder init params to match llama.cpp order

  abetlen

  committed
  6a20293

  Copy full SHA for 6a20293

• Explicitly make all init params other than model_path into keyword only params

  abetlen

  committed
  c8f9b8a

  Copy full SHA for c8f9b8a

Pagination

Previous

Next