]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2023-04-14 Pavol Rusnakpy : cleanup dependencies (#962)
2023-04-14 Pavol Rusnakpy : fix flake8 and isort nitpicks (#960)
2023-04-14 Georgi Gerganovggml : minor
2023-04-14 Georgi Gerganovggml : always allocate buffers with size multiple of...
2023-04-14 comexpy : new conversion script (#545)
2023-04-14 Georgi Gerganovggml : fix q4_1 dot product types
2023-04-14 Howard Suggml : optimize rope function to avoid call powf in...
2023-04-13 Gary Linscottperplexity : add support for batch size to `--perplexit...
2023-04-13 CRD716common : remove unnecessary includes (#947)
2023-04-13 Georgi Gerganovggml : add GGML_DEFAULT_N_THREADS
2023-04-13 Georgi Gerganovggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit...
2023-04-13 Georgi Gerganovllama : merge llama_internal.h into llama.h
2023-04-13 Georgi Gerganovgitignore : benchmark
2023-04-13 Stephan Walterggml : optimize non-SIMD Q4_0 vector dot product (...
2023-04-13 Pavol Rusnakggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE...
2023-04-13 CRD716fix whitespace (#944)
2023-04-13 CRD716readme : remove python 3.10 warning (#929)
2023-04-13 Genkagaku.GPTreadme : llama node binding (#911)
2023-04-13 Pavol Rusnakflake.nix: add all binaries from bin (#848)
2023-04-13 Juddzig : update build.zig (#872)
2023-04-13 Vladimirggml : update cblas_sgemm columns var to be more reason...
2023-04-13 niansa/tuxifanexamples : add -n to alpaca and gpt4all scripts (#706)
2023-04-13 anzz1cmake : add explicit F16C option (x86) (#576)
2023-04-13 SebastianApelbenchmark : add tool for timing q4_0 matrix multiplicat...
2023-04-13 Pavol Rusnakdo not force the prompt file to end with a new line...
2023-04-12 Stephan WalterDon't crash on ftype (formerly f16) == 4 (#917)
2023-04-12 Georgi Gerganovreadme : change "GPU support" link to discussion
2023-04-12 Georgi Gerganovreadme : update hot topics with link to "GPU support...
2023-04-12 Nicolai Weitkemperreadme: link to sha256sums file (#902)
2023-04-11 Pavol RusnakFix whitespace, add .editorconfig, add GitHub workflow...
2023-04-11 Stephan WalterAdd enum llama_ftype, sync ggml_type to model files...
2023-04-11 comexWindows fixes (#890)
2023-04-10 qouoqAdd BAIR's Koala to supported models (#877)
2023-04-10 Georgi Gerganovggml : fix WASM build
2023-04-10 Georgi Gerganovggml : add ggml_cont() + optimize ggml_cpy() for contig...
2023-04-10 Georgi Gerganovggml : remove trailing whitespaces
2023-04-10 Marco MatthiesSimplify to include lower-case windows.h always, fix...
2023-04-10 Georgi Gerganovggml : fix quantize_row_q4_1() ARM_NEON (close #876)
2023-04-09 comexPrint model version.
2023-04-09 comexRewrite loading code to try to satisfy everyone:
2023-04-08 Tomáš Pazdiorafix for windows utf-8 input (#840)
2023-04-08 eierycmake should link openblas properly with -lopenblas...
2023-04-08 lonAdd new binaries to flake.nix (#847)
2023-04-07 unboundedAdd quantize-stats command for testing quantization...
2023-04-07 bhubbbmake : add libllama.so target for llama-cpp-python...
2023-04-07 iacorezig : don't link examples/common.cpp for non-example...
2023-04-07 Ivan Stepanovllama : always sort logits before nucleus sampling...
2023-04-06 Sergey AlirzaevDo not crash when it has nothing to say. (#796)
2023-04-06 Pavol RusnakMake docker instructions more explicit (#785)
2023-04-05 Georgi Gerganovggml : multi-thread ggml_rope() (~3-4 times faster...
2023-04-05 Georgi Gerganovggml, llama : avoid heavy V transpose + improvements...
2023-04-05 Georgi GerganovUpdate README.md
2023-04-05 Ivan Stepanovllama : define non-positive top_k; top_k range check...
2023-04-05 at8umiku.sh : add executable bit (#780)
2023-04-05 Georgi Gerganovmedia : add logos and banners
2023-04-05 Georgi Gerganovreadme : change logo + add bindings + add uis + add...
2023-04-05 iacorezig : add build.zig (#773)
2023-04-05 Ivan Stepanovmake : missing host optimizations in CXXFLAGS (#763)
2023-04-05 Adithya Balajireadme : update with CMake and windows example (#748)
2023-04-05 at8uexamples : add Miku.sh (#724)
2023-04-05 Andrew DuffyAdd Accelerate/BLAS when using Swift (#765)
2023-04-03 mgroeber9110Windows: reactive sigint handler after each Ctrl-C...
2023-04-03 SebastianApel10+% performance improvement of ggml_vec_dot_q4_0 on...
2023-04-03 Ivan StepanovDefine non-positive temperature behavior (#720)
2023-04-02 bsilvereagleRemove torch GPU dependencies from the Docker.full...
2023-04-02 Thatcher ChamberlinAdd a missing step to the gpt4all instructions (#690)
2023-04-02 Christian FalchAdded api for getting/setting the kv_cache (#685)
2023-04-02 Marian Cepokggml : change ne to int64_t (#626)
2023-04-02 Leonardo Neumannexamples : add gpt4all script (#658)
2023-04-02 Stephan Walterllama : do not allocate KV cache for "vocab_only =...
2023-04-02 Fabianmake : use -march=native -mtune=native on x86 (#609)
2023-04-02 Murilo Santanafix default params for examples/main (#697)
2023-04-01 Ikko Eltociear... py: huggingface -> Hugging Face (#686)
2023-04-01 rimoligareadme: replace termux links with homepage, play store...
2023-04-01 SlarenShow error message when -f fails
2023-03-31 Stephan WalterEnable -std= for cmake builds, fix warnings (#598)
2023-03-31 slarenOptimize AVX2 ggml_vec_dot_q4_0 (#642)
2023-03-31 perserkAdd AVX acceleration (#617)
2023-03-31 Pavol Rusnakpy : cleanup the code
2023-03-30 Pavol Rusnakdrop quantize.py (now that models are using a single...
2023-03-30 Georgi Gerganovreadme : update supported models
2023-03-30 Justine TunneyIntroduce GGML migration tool for new file format
2023-03-30 Justine TunneyEnsure --mlock works properly with mmap() support
2023-03-30 Justine TunneyMake loading weights 10-100x faster
2023-03-30 SlarenInitial windows support (untested)
2023-03-30 SlarenAlways initialize mm_addr and mm_length in llama_model
2023-03-30 SlarenUnmap the file in llama_free
2023-03-30 SlarenMake mmap_file static
2023-03-30 SlarenFix ggml_init_params in quantize
2023-03-30 SlarenAdd mmap support for model files
2023-03-30 Stephan Waltercmake : properly invoke CTest (#629)
2023-03-30 Casey PrimozicRemove unused variable (#607)
2023-03-30 david raistrickmake : fix darwin f16c flags check (#615)
2023-03-30 Georgi Gerganovggml : fix NEON signs (close #620, #622)
2023-03-30 slarenFix GGML_F32Cx8_STORE in AVX without F16C path (#619)
2023-03-29 anzz1ci : re-enable AVX512 testing (Windows-MSVC) (#584)
2023-03-29 Georgi Gerganovggml : init time on first ggml_init() call
2023-03-29 Georgi Gerganovllama : fix compile warnings when reading the vocab
2023-03-29 Georgi Gerganovggml : add ARM_NEON dequantize_row_q4_1()
2023-03-29 Georgi Gerganovggml : add ARM_NEON quantize_row_q4_1()
next