 Hua Jiang
|
0ccfc62a96
ggml_tensor: update the structure comments. (#3283)
|
2 years ago |
 Qu Zongfu
|
7f1a0fe709
ggml : release the requested thread pool resource (#3292)
|
2 years ago |
 slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 years ago |
 Eve
|
0512d66670
ci : multithreaded builds (#3311)
|
2 years ago |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
2 years ago |
 Cebtenzzre
|
2db94d98ed
gguf : basic type checking in gguf_get_* (#3346)
|
2 years ago |
|
Cebtenzzre
|
ecf90b1a51
gguf : make token scores and types optional (#3347)
|
2 years ago |
 Georgi Gerganov
|
2619109ad5
ci : disable freeBSD builds due to lack of VMs (#3381)
|
2 years ago |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 years ago |
 Kevin Ji
|
45855b3f1c
docs : mark code as Bash (#3375)
|
2 years ago |
 Pierre Alexandre SCHEMBRI
|
4aea3b846e
readme : add Mistral AI release 0.1 (#3362)
|
2 years ago |
|
slaren
|
da0400344b
ggml-cuda : perform cublas fp16 matrix multiplication as fp16 (#3370)
|
2 years ago |
 Zhang Peiyuan
|
e519621010
convert : remove bug in convert.py permute function (#3364)
|
2 years ago |
 Richard Roberson
|
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290)
|
2 years ago |
|
Cebtenzzre
|
20c7e1e804
gguf : fix a few general keys (#3341)
|
2 years ago |
 Rickard Hallerbäck
|
dc6897404e
metal : reusing llama.cpp logging (#3152)
|
2 years ago |
 Jag Chadha
|
527e57cfd8
build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (#3342)
|
2 years ago |
 BarfingLemurs
|
ffe88a36a9
readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (#3340)
|
2 years ago |
 DAN™
|
99115f3fa6
cmake : fix build-info.h on MSVC (#3309)
|
2 years ago |
 2f38b454
|
1726f9626f
docs: Fix typo CLBlast_DIR var. (#3330)
|
2 years ago |
 Erik Scholz
|
a98b1633d5
nix : add cuda, use a symlinked toolkit for cmake (#3202)
|
2 years ago |
|
slaren
|
c091cdfb24
llama-bench : add README (#3317)
|
2 years ago |
|
Cebtenzzre
|
51a7cf5c6e
examples : fix RoPE defaults to match PR #3240 (#3315)
|
2 years ago |
|
Kevin Ji
|
bedb92b603
scripts : use `/usr/bin/env` in shebang (#3313)
|
2 years ago |
 Lee Drake
|
bc9d3e3971
Update README.md (#3289)
|
2 years ago |
 shibe2
|
36b904e200
ggml-opencl.cpp: Make private functions static (#3300)
|
2 years ago |
 Edward Taylor
|
324f3403d5
zig : fix for updated c lib (#3259)
|
2 years ago |
 yuiseki
|
f56c418ab0
embedding : update README.md (#3224)
|
2 years ago |
 Johannes Gäßler
|
8185710a80
CUDA: use only 1 thread if fully offloaded (#2915)
|
2 years ago |
|
Georgi Gerganov
|
7eb41179ed
readme : update hot topics
|
2 years ago |
