 bandoti
|
095231dfd3
cmake : fix transient definitions in find pkg (#3411)
|
пре 2 година |
 Kevin Ji
|
ea55295a74
docker : ignore Git files (#3314)
|
пре 2 година |
 vvhg1
|
c97f01c362
infill : add new example + extend server API (#3296)
|
пре 2 година |
 slaren
|
f5ef5cfb18
ggml-cuda : perform cublas mat mul of quantized types as f16 (#3412)
|
пре 2 година |
|
slaren
|
40e07a60f9
llama.cpp : add documentation about rope_freq_base and scale values (#3401)
|
пре 2 година |
 Georgi Gerganov
|
bc34dd4f5b
train : fix KQ_pos allocation (#3392)
|
пре 2 година |
 Cebtenzzre
|
2777a84be4
llama : quantize up to 31% faster on Linux and Windows with mmap (#3206)
|
пре 2 година |
 BarfingLemurs
|
0a4a4a0982
readme : update hot topics + model links (#3399)
|
пре 2 година |
 Andrew Duffy
|
569550df20
readme : add link to grammars app (#3388)
|
пре 2 година |
 Jhen-Jie Hong
|
c71bf2c45c
swift : fix build on xcode 15 (#3387)
|
пре 2 година |
|
Cebtenzzre
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
пре 2 година |
 Hua Jiang
|
0ccfc62a96
ggml_tensor: update the structure comments. (#3283)
|
пре 2 година |
 Qu Zongfu
|
7f1a0fe709
ggml : release the requested thread pool resource (#3292)
|
пре 2 година |
|
slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
пре 2 година |
 Eve
|
0512d66670
ci : multithreaded builds (#3311)
|
пре 2 година |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
пре 2 година |
|
Cebtenzzre
|
2db94d98ed
gguf : basic type checking in gguf_get_* (#3346)
|
пре 2 година |
|
Cebtenzzre
|
ecf90b1a51
gguf : make token scores and types optional (#3347)
|
пре 2 година |
|
Georgi Gerganov
|
2619109ad5
ci : disable freeBSD builds due to lack of VMs (#3381)
|
пре 2 година |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
пре 2 година |
|
Kevin Ji
|
45855b3f1c
docs : mark code as Bash (#3375)
|
пре 2 година |
 Pierre Alexandre SCHEMBRI
|
4aea3b846e
readme : add Mistral AI release 0.1 (#3362)
|
пре 2 година |
|
slaren
|
da0400344b
ggml-cuda : perform cublas fp16 matrix multiplication as fp16 (#3370)
|
пре 2 година |
 Zhang Peiyuan
|
e519621010
convert : remove bug in convert.py permute function (#3364)
|
пре 2 година |
 Richard Roberson
|
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290)
|
пре 2 година |
|
Cebtenzzre
|
20c7e1e804
gguf : fix a few general keys (#3341)
|
пре 2 година |
 Rickard Hallerbäck
|
dc6897404e
metal : reusing llama.cpp logging (#3152)
|
пре 2 година |
 Jag Chadha
|
527e57cfd8
build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (#3342)
|
пре 2 година |
|
BarfingLemurs
|
ffe88a36a9
readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (#3340)
|
пре 2 година |
 DAN™
|
99115f3fa6
cmake : fix build-info.h on MSVC (#3309)
|
пре 2 година |
