| .. |
|
CMakeLists.txt
|
97bbca6e85
cmake : fix ld warning duplicate libraries libllama.a (#4671)
|
vor 2 Jahren |
|
test-backend-ops.cpp
|
147b17ac94
2-bit quantizations (#4897)
|
vor 2 Jahren |
|
test-c.c
|
849408957c
tests : add a C compliance test (#2848)
|
vor 2 Jahren |
|
test-double-float.cpp
|
207b51900e
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
|
vor 2 Jahren |
|
test-grad0.cpp
|
5bf3953d7e
cuda : improve cuda pool efficiency using virtual memory (#4606)
|
vor 2 Jahren |
|
test-grammar-parser.cpp
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
vor 2 Jahren |
|
test-llama-grammar.cpp
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
vor 2 Jahren |
|
test-opt.cpp
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
vor 2 Jahren |
|
test-quantize-fns.cpp
|
49662cbed3
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
|
vor 2 Jahren |
|
test-quantize-perf.cpp
|
6744dbe924
ggml : use ggml_row_size where possible (#4472)
|
vor 2 Jahren |
|
test-rope.cpp
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
vor 2 Jahren |
|
test-sampling.cpp
|
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696)
|
vor 2 Jahren |
|
test-tokenizer-0-falcon.cpp
|
233fc1c69f
Minor improvements in GPT2 tokenizer (#3567)
|
vor 2 Jahren |
|
test-tokenizer-0-falcon.py
|
f23c0359a3
ci : add flake8 to github actions (python linting) (#4129)
|
vor 2 Jahren |
|
test-tokenizer-0-llama.cpp
|
233fc1c69f
Minor improvements in GPT2 tokenizer (#3567)
|
vor 2 Jahren |
|
test-tokenizer-0-llama.py
|
f23c0359a3
ci : add flake8 to github actions (python linting) (#4129)
|
vor 2 Jahren |
|
test-tokenizer-1-bpe.cpp
|
daab3d7f45
Add more tokenizer tests (#3742)
|
vor 2 Jahren |
|
test-tokenizer-1-llama.cpp
|
ff5a3f0c09
Work on the BPE tokenizer (#3252)
|
vor 2 Jahren |
Kawrakow
147b17ac94
2-bit quantizations (#4897)