| .. |
|
CMakeLists.txt
|
1d656d6360
ggml : change ggml_graph_compute() API to not require context (#1999)
|
2 years ago |
|
test-double-float.c
|
436e561931
all : be more strict about converting float to double (#458)
|
2 years ago |
|
test-grad0.c
|
20d7740a9b
ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183)
|
2 years ago |
|
test-opt.c
|
20d7740a9b
ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183)
|
2 years ago |
|
test-quantize-fns.cpp
|
1b107b8550
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
|
2 years ago |
|
test-quantize-perf.cpp
|
1b107b8550
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
|
2 years ago |
|
test-sampling.cpp
|
b061ba9e2a
llama : fix top-p sampling to match the canonical definition (#1953)
|
2 years ago |
|
test-tokenizer-0.cpp
|
5656d10599
mpi : add support for distributed inference via MPI (#2099)
|
2 years ago |
Georgi Gerganov
20d7740a9b
ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183)