| .. |
|
CMakeLists.txt
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
hace 2 años |
|
test-double-float.c
|
436e561931
all : be more strict about converting float to double (#458)
|
hace 2 años |
|
test-grad0.c
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
hace 2 años |
|
test-opt.c
|
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)
|
hace 2 años |
|
test-quantize-fns.cpp
|
7a32fcb3b2
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
|
hace 2 años |
|
test-quantize-perf.cpp
|
c50b628810
Fix CI: ARM NEON, quantization unit tests, editorconfig (#1122)
|
hace 2 años |
|
test-sampling.cpp
|
3924088512
Remove default arguments from sampling functions (#1343)
|
hace 2 años |
|
test-tokenizer-0.cpp
|
efd05648c8
llama : well-defined static initialization of complex objects (#927)
|
hace 2 años |
xaedes
f954edda93
ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)