Commits

Commits on Dec 22, 2023

Update bug report instructions for new build process.
abetlen
committed
f6f157c
Copy full SHA for f6f157c
Add HIP_PATH to dll search directories for windows users.
abetlen
committed
92284f3
Copy full SHA for 92284f3
set llama_max_devices using library function
abetlen
committed
2b0d3f3
Copy full SHA for 2b0d3f3
Fix typo
abetlen
committed
d9a1d90
Copy full SHA for d9a1d90
Bump version
abetlen
committed
37556bf
Copy full SHA for 37556bf
fix: inccorect bindings for kv override. Based on #1011
abetlen
committed
6d8bc09
Copy full SHA for 6d8bc09
Fix typo
abetlen
committed
f4be84c
Copy full SHA for f4be84c
docs: Add multi-model link to readme
abetlen
committed
9b3a593
Copy full SHA for 9b3a593
docs: add server config docs
abetlen
committed
522aecb
Copy full SHA for 522aecb
Update llama.cpp
abetlen
committed
6473796
Copy full SHA for 6473796
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
abetlen
committed
15ee210
Copy full SHA for 15ee210
server: Support none defaulting to infinity for completions (#111)
Show description for 4b01a87

swg
and
abetlen
authored
4b01a87
Copy full SHA for 4b01a87
Check if completion_tokens is none in error handler.
abetlen
committed
99ff175
Copy full SHA for 99ff175
[Feat] Multi model support (#931)
Show description for 12b7f2f

D4ve-R
and
abetlen
authored
12b7f2f
Copy full SHA for 12b7f2f
Update llama.cpp
abetlen
committed
4a85442
Copy full SHA for 4a85442
fix text_offset of multi-token characters (#1037)
Show description for 2f03fb0
twaka
authored
2f03fb0
Copy full SHA for 2f03fb0

Commits on Dec 21, 2023

Implement openai api compatible authentication (#1010)
docmeth02
authored
33cc623
Copy full SHA for 33cc623
Update llama.cpp
abetlen
committed
788394c
Copy full SHA for 788394c

Commits on Dec 19, 2023

Update llama.cpp
abetlen
committed
ffceb77
Copy full SHA for ffceb77

Commits on Dec 18, 2023

fix: float32 is not JSON serializable when streaming logits.
abetlen
committed
a05b4da
Copy full SHA for a05b4da
Update changelog
abetlen
committed
abda047
Copy full SHA for abda047
Fix type annotations
abetlen
committed
7df6c32
Copy full SHA for 7df6c32
Fix type annotation
abetlen
committed
b703aad
Copy full SHA for b703aad
Fix type annotation
abetlen
committed
d0aedfc
Copy full SHA for d0aedfc
Fix ctypes definitions of `llama_kv_cache_view_update` and `llama_kv_cache_view_free`. (#1028)
e-c-d
authored
2993936
Copy full SHA for 2993936
Bump version
abetlen
committed
5e863d8
Copy full SHA for 5e863d8
Update low_level_api_llama_cpp.py to match current API (#1023)
jsoma
authored
cfd698c
Copy full SHA for cfd698c
Add offload_kqv option to llama and server
abetlen
committed
095c650
Copy full SHA for 095c650
Remove unnused import
abetlen
committed
472b344
Copy full SHA for 472b344
Update llama.cpp
abetlen
committed
2fc48c5
Copy full SHA for 2fc48c5
perf: Don't convert logprobs arrays to lists (#1021)
kddubey
authored
6b2e0e0
Copy full SHA for 6b2e0e0
Bugfix: Remove f16_kv, add offload_kqv field (#1019)
Show description for 62944df
brandonrobertz
authored
62944df
Copy full SHA for 62944df

Commits on Dec 17, 2023

Update README.md functionary demo typo (#996)
Show description for 37da8e8
evelynmitchell
authored
37da8e8
Copy full SHA for 37da8e8

Commits on Dec 16, 2023

Bug fixed with n_ctx=0 (#1015)
Show description for f1c631d
DanieleMorotti
authored
f1c631d
Copy full SHA for f1c631d
Fix logits_to_logprobs for 2-D and 3-D logits (#1002)
Show description for 5a89446
kddubey
authored
5a89446
Copy full SHA for 5a89446