Commits

Branch selector

 v0.2.4

User selector

All users

Datepicker

All time

Commit History

Commits on Sep 14, 2023

• 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

• Add kwargs to init to catch extra params

  abetlen

  committed
  a68f9e2

  Copy full SHA for a68f9e2

• remove print

  abetlen

  committed
  9e345a4

  Copy full SHA for 9e345a4

• Convert missed llama.cpp constants into standard python types

  abetlen

  committed
  517f9ed

  Copy full SHA for 517f9ed

• Fix tensor_split cli option

  abetlen

  committed
  c4c440b

  Copy full SHA for c4c440b

Commits on Sep 13, 2023

• Bump version

  abetlen

  committed
  203ede4

  Copy full SHA for 203ede4

• Fix issue with Literal and Optional cli arguments not working. Closes #702

  abetlen

  committed
  759405c

  Copy full SHA for 759405c

• Add pyproject extra for scikit-build-core to ensure compatible pathspec version

  abetlen

  committed
  6cfc542

  Copy full SHA for 6cfc542

• Update llama.cpp

  abetlen

  committed
  cacfd56

  Copy full SHA for cacfd56

• Add X-Request-ID request header for mirroring custom IDs. (#703)

  devrimcavusoglu

  authored
  da9df78

  Copy full SHA for da9df78

• Update CHANGELOG

  abetlen

  committed
  1372e4f

  Copy full SHA for 1372e4f

• Bump version

  abetlen

  committed
  8e13520

  Copy full SHA for 8e13520

• fix: only ignore c extension files installed in-source, avoids removing ggml-metal.metal from sdist

  abetlen

  committed
  ec11320

  Copy full SHA for ec11320

• Remove reference to FORCE_CMAKE from docs

  abetlen

  committed
  8ddf63b

  Copy full SHA for 8ddf63b

• docs: Use pymdownx.snippets for easier docs management

  abetlen

  committed
  109123c

  Copy full SHA for 109123c

• Bump version

  abetlen

  committed
  2787663

  Copy full SHA for 2787663

• Update CHANGELOG

  abetlen

  committed
  38cd2ac

  Copy full SHA for 38cd2ac

• bugfix: remove git directories from source distribution to avoid build-info.h bug

  abetlen

  committed
  6e02525

  Copy full SHA for 6e02525

Commits on Sep 12, 2023

• Add python version classifiers to pyproject.toml

  abetlen

  committed
  c59f084

  Copy full SHA for c59f084

• Merge pull request #499 from abetlen/v0.2-wip

  Show description for 3feeafe
  abetlen

  authored
  3feeafe

  Copy full SHA for 3feeafe

• Update title

  abetlen

  committed
  bcef9ab

  Copy full SHA for bcef9ab

• Remove references to force_cmake

  abetlen

  committed
  89ae347

  Copy full SHA for 89ae347

• Remove references to FORCE_CMAKE

  abetlen

  committed
  1dd3f47

  Copy full SHA for 1dd3f47

• Bump version

  abetlen

  committed
  6e89775

  Copy full SHA for 6e89775

Pagination

Previous

Next