cturan/llama.cpp @ 41a11aaf99feff4901e4c8dc48ad00766c5da4e9

Georgi Gerganov fe680e3d10 sync : ggml (new ops, tests, backend, etc.) (#4359)		2 年之前
..
CMakeLists.txt	fe680e3d10 sync : ggml (new ops, tests, backend, etc.) (#4359)	2 年之前
test-backend-ops.cpp	fe680e3d10 sync : ggml (new ops, tests, backend, etc.) (#4359)	2 年之前
test-c.c	849408957c tests : add a C compliance test (#2848)	2 年之前
test-double-float.cpp	207b51900e ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)	2 年之前
test-grad0.cpp	4760e7cc0b sync : ggml (backend v2) (#3912)	2 年之前
test-grammar-parser.cpp	6381d4e110 gguf : new file format with flexible meta data (beta) (#2398)	2 年之前
test-llama-grammar.cpp	6381d4e110 gguf : new file format with flexible meta data (beta) (#2398)	2 年之前
test-opt.cpp	4760e7cc0b sync : ggml (backend v2) (#3912)	2 年之前
test-quantize-fns.cpp	207b51900e ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)	2 年之前
test-quantize-perf.cpp	f93af02488 sync : ggml (conv 1d + 2d updates, UB fixes) (#3468)	2 年之前
test-rope.cpp	ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228)	2 年之前
test-sampling.cpp	d1031cf49c sampling : refactor init to use llama_sampling_params (#3696)	2 年之前
test-tokenizer-0-falcon.cpp	233fc1c69f Minor improvements in GPT2 tokenizer (#3567)	2 年之前
test-tokenizer-0-falcon.py	f23c0359a3 ci : add flake8 to github actions (python linting) (#4129)	2 年之前
test-tokenizer-0-llama.cpp	233fc1c69f Minor improvements in GPT2 tokenizer (#3567)	2 年之前
test-tokenizer-0-llama.py	f23c0359a3 ci : add flake8 to github actions (python linting) (#4129)	2 年之前
test-tokenizer-1-bpe.cpp	daab3d7f45 Add more tokenizer tests (#3742)	2 年之前
test-tokenizer-1-llama.cpp	ff5a3f0c09 Work on the BPE tokenizer (#3252)	2 年之前