Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Apr 25, 2023

• Update n_batch for server

  abetlen

  committed
  3cab3ef

  Copy full SHA for 3cab3ef

• Add ctx check and re-order __init__. Closes #112

  abetlen

  committed
  cc706fb

  Copy full SHA for cc706fb

• Bump version

  abetlen

  committed
  996e31d

  Copy full SHA for 996e31d

• Add FORCE_CMAKE option

  abetlen

  committed
  848c83d

  Copy full SHA for 848c83d

• Bump version

  abetlen

  committed
  9dddb3a

  Copy full SHA for 9dddb3a

• Bugfix: Check cache keys as prefix to prompt tokens

  abetlen

  committed
  d484c56

  Copy full SHA for d484c56

Commits on Apr 24, 2023

• Update docs

  abetlen

  committed
  b75fa96

  Copy full SHA for b75fa96

• Add cache implementation using llama state

  abetlen

  committed
  cbe95bb

  Copy full SHA for cbe95bb

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

  abetlen

  committed
  2c359a2

  Copy full SHA for 2c359a2

• Add save/load state api for Llama class

  abetlen

  committed
  197cf80

  Copy full SHA for 197cf80

• Update llama.cpp

  abetlen

  committed
  c4c332f

  Copy full SHA for c4c332f

• Update llama.cpp

  abetlen

  committed
  280a047

  Copy full SHA for 280a047

• Refactor internal state for Llama class

  abetlen

  committed
  86f8e5a

  Copy full SHA for 86f8e5a

• Merge pull request #108 from eiery/main

  Show description for f374561
  abetlen

  authored
  f374561

  Copy full SHA for f374561

• Update llama.cpp

  abetlen

  committed
  02cf881

  Copy full SHA for 02cf881

• Update llama.py

  Show description for aa12d8a
  

  eiery

  authored
  aa12d8a

  Copy full SHA for aa12d8a

Commits on Apr 23, 2023

• Disable mmap when applying lora weights. Closes #107

  abetlen

  committed
  7230599

  Copy full SHA for 7230599

Commits on Apr 22, 2023

• Update llama.cpp

  abetlen

  committed
  e99caed

  Copy full SHA for e99caed

Commits on Apr 21, 2023

• Bump version

  abetlen

  committed
  643b73e

  Copy full SHA for 643b73e

• Update llama.cpp

  abetlen

  committed
  1eb130a

  Copy full SHA for 1eb130a

Commits on Apr 20, 2023

• Update llama.cpp

  abetlen

  committed
  ba3959e

  Copy full SHA for ba3959e

• Bump version

  abetlen

  committed
  207adbd

  Copy full SHA for 207adbd

• Update llama.cpp

  abetlen

  committed
  3d29062

  Copy full SHA for 3d29062

Commits on Apr 19, 2023

• Add use_mmap flag to server

  abetlen

  committed
  e4647c7

  Copy full SHA for e4647c7

• Update llama.cpp

  abetlen

  committed
  207ebbc

  Copy full SHA for 207ebbc

• If lora base is not set avoid re-loading the model by passing NULL

  abetlen

  committed
  0df4d69

  Copy full SHA for 0df4d69

• Update type signature to allow for null pointer to be passed.

  abetlen

  committed
  95c0dc1

  Copy full SHA for 95c0dc1

Commits on Apr 18, 2023

• Add seperate lora_base path for applying LoRA to quantized models using original unquantized model weights.

  abetlen

  committed
  453e517

  Copy full SHA for 453e517

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

  abetlen

  committed
  32ca803

  Copy full SHA for 32ca803

• Update llama.cpp

  abetlen

  committed
  b2d44aa

  Copy full SHA for b2d44aa

• Merge pull request #87 from SagsMug/main

  Show description for 4ce6670
  abetlen

  authored
  4ce6670

  Copy full SHA for 4ce6670

• Add lora_path parameter to Llama model

  abetlen

  committed
  eb7f278

  Copy full SHA for eb7f278

• Add bindings for LoRA adapters. Closes #88

  abetlen

  committed
  35abf89

  Copy full SHA for 35abf89

• Update llama.cpp

  abetlen

  committed
  3f68e95

  Copy full SHA for 3f68e95

Commits on Apr 17, 2023

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

  

  Mug

  committed
  1b73a15

  Copy full SHA for 1b73a15

Pagination

Previous

Next