Georgi Gerganov 880eee64f1 ci : integrate with ggml-org/ci (#2250) ...

* ci : run ctest

ggml-ci

* ci : add open llama 3B-v2 tests

ggml-ci

* ci : disable wget progress output

ggml-ci

* ci : add open llama 3B-v2 tg tests for q4 and q5 quantizations

ggml-ci

* tests : try to fix tail free sampling test

ggml-ci

* ci : add K-quants

ggml-ci

* ci : add short perplexity tests

ggml-ci

* ci : add README.md

* ppl : add --chunks argument to limit max number of chunks

ggml-ci

* ci : update README

2023-07-18 14:24:43 +03:00

..

CMakeLists.txt

ggml : change ggml_graph_compute() API to not require context (#1999)

2023-07-07 19:24:01 +03:00

test-double-float.c

all : be more strict about converting float to double (#458)

2023-03-28 19:48:20 +03:00

test-grad0.c

ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183)

2023-07-11 22:53:34 +03:00

test-opt.c

ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183)

2023-07-11 22:53:34 +03:00

test-quantize-fns.cpp

ggml : generalize quantize_fns for simpler FP16 handling (#1237)

2023-07-05 19:13:06 +03:00

test-quantize-perf.cpp

ggml : generalize quantize_fns for simpler FP16 handling (#1237)

2023-07-05 19:13:06 +03:00

test-sampling.cpp

ci : integrate with ggml-org/ci (#2250)

2023-07-18 14:24:43 +03:00

test-tokenizer-0.cpp

mpi : add support for distributed inference via MPI (#2099)

2023-07-10 18:49:56 +03:00