COMMITS
December 22, 2023
A
Bump version
Andrei Betlen committed
A
fix: inccorect bindings for kv override. Based on #1011
Andrei Betlen committed
A
docs: Add multi-model link to readme
Andrei Betlen committed
A
docs: add server config docs
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
A
Check if completion_tokens is none in error handler.
Andrei Betlen committed
D
[Feat] Multi model support (#931)
Dave committed
A
Update llama.cpp
Andrei Betlen committed
T
fix text_offset of multi-token characters (#1037)
twaka committed
December 21, 2023
D
Implement openai api compatible authentication (#1010)
docmeth02 committed
A
Update llama.cpp
Andrei Betlen committed
December 19, 2023
A
Update llama.cpp
Andrei Betlen committed
December 18, 2023
A
fix: float32 is not JSON serializable when streaming logits.
Andrei Betlen committed
A
Update changelog
Andrei Betlen committed
A
Fix type annotations
Andrei Betlen committed
A
Fix type annotation
Andrei Betlen committed
A
Fix type annotation
Andrei Betlen committed
E
Fix ctypes definitions of `llama_kv_cache_view_update` and `llama_kv_cache_view_free`. (#1028)
Eduard Christian Dumitrescu committed
A
Bump version
Andrei Betlen committed
J
Update low_level_api_llama_cpp.py to match current API (#1023)
Jonathan Soma committed
A
Add offload_kqv option to llama and server
Andrei Betlen committed
A
Remove unnused import
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed
K
perf: Don't convert logprobs arrays to lists (#1021)
kddubey committed
B
Bugfix: Remove f16_kv, add offload_kqv field (#1019)
Brandon Roberts committed
December 17, 2023
E
Update README.md functionary demo typo (#996)
evelynmitchell committed
December 16, 2023
D
Bug fixed with n_ctx=0 (#1015)
Daniele Morotti committed