Michael Klimenko 52bb63c708 refactor : switch to emplace_back to avoid extra object (#5291) 1 éve
..
.gitignore 3b7c914de2 tests : gitignore test-c.o 2 éve
CMakeLists.txt 413e7b0559 ci : add model tests + script wrapper (#4586) 2 éve
get-model.cpp 413e7b0559 ci : add model tests + script wrapper (#4586) 2 éve
get-model.h 413e7b0559 ci : add model tests + script wrapper (#4586) 2 éve
test-autorelease.cpp 413e7b0559 ci : add model tests + script wrapper (#4586) 2 éve
test-backend-ops.cpp 15606309a0 llava : add MobileVLM support (#5132) 1 éve
test-c.c fbf1ddec69 Nomic Vulkan backend (#4456) 1 éve
test-double-float.cpp 207b51900e ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861) 2 éve
test-grad0.cpp 5bf3953d7e cuda : improve cuda pool efficiency using virtual memory (#4606) 2 éve
test-grammar-parser.cpp 6381d4e110 gguf : new file format with flexible meta data (beta) (#2398) 2 éve
test-llama-grammar.cpp 52bb63c708 refactor : switch to emplace_back to avoid extra object (#5291) 1 éve
test-model-load-cancel.cpp 413e7b0559 ci : add model tests + script wrapper (#4586) 2 éve
test-opt.cpp 4760e7cc0b sync : ggml (backend v2) (#3912) 2 éve
test-quantize-fns.cpp f4d7e54974 SOTA 3-bit quants (#5196) 1 éve
test-quantize-perf.cpp f4d7e54974 SOTA 3-bit quants (#5196) 1 éve
test-rope.cpp ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) 2 éve
test-sampling.cpp b2b2bf988c Tests for min_p, sampling queue (#5147) 2 éve
test-tokenizer-0-falcon.cpp 233fc1c69f Minor improvements in GPT2 tokenizer (#3567) 2 éve
test-tokenizer-0-falcon.py f23c0359a3 ci : add flake8 to github actions (python linting) (#4129) 2 éve
test-tokenizer-0-llama.cpp 233fc1c69f Minor improvements in GPT2 tokenizer (#3567) 2 éve
test-tokenizer-0-llama.py f23c0359a3 ci : add flake8 to github actions (python linting) (#4129) 2 éve
test-tokenizer-1-bpe.cpp daab3d7f45 Add more tokenizer tests (#3742) 2 éve
test-tokenizer-1-llama.cpp ff5a3f0c09 Work on the BPE tokenizer (#3252) 2 éve