]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2023-03-29 Pavol Rusnakrename convert_ggml_to_pth.py -> convert-ggml-to-pth...
2023-03-29 ThérenceCreate chat-13B.bat (#592)
2023-03-29 Georgi Gerganovreadme : fix typos
2023-03-29 Georgi Gerganovreadme : add GPT4All instructions (close #588)
2023-03-29 Georgi Gerganovpy : add GPT4All conversion script
2023-03-29 Maël Kerbirioullama : use the same threshold for OpenBLAS and ggml...
2023-03-29 Tobias Lütkeadd example of re-act pattern (#583)
2023-03-29 anzz1Fix GCC warning about binary literal (#595)
2023-03-29 anzz1Fix typo in llama.h (#593)
2023-03-28 anzz1Enable Fused-Multiply-Add (FMA) and F16C/CVT16 vector...
2023-03-28 anzz1CI: fix subdirectory path globbing (#546)
2023-03-28 anzz1llama : fix linkage with mingw (#551)
2023-03-28 slarenggml : add AVX2 implementation of quantize_row_q4_1...
2023-03-28 thementpy : add temporary script to convert old ggml files...
2023-03-28 Tai Duc Nguyenpy : add capabiliy to convert from ggml back to torch...
2023-03-28 Stephan Walterggml : refactor quantized processing functions (#509)
2023-03-28 DooWoong Lee... py : removed unused `model` variable and verified that...
2023-03-28 Georgi Gerganovci : make ctest verbose, hopefully we see what is wrong...
2023-03-28 Georgi Gerganovtests : free llama context at the end of the test
2023-03-28 Stephan Walterall : be more strict about converting float to double...
2023-03-28 Jed Foxdeploy : add a Package.swift for SwiftPM support (...
2023-03-28 Stephan Walterggml : introduce structs for the q4 data blocks (#356)
2023-03-28 Georgi Gerganovgitignore : add "embedding"
2023-03-28 dotpy314Check the existence of f16_model_path_base in quantize...
2023-03-28 slarenFix usage of F16C intrinsics in AVX code (#563)
2023-03-28 anzz1main.cpp fixes, refactoring (#571)
2023-03-28 RJ AdriaansenAdd embedding example to Makefile (#540)
2023-03-27 Marco MatthiesFix missing ggml link in cmake for examples/* on w64...
2023-03-26 Erik Scholzci: add debug build to sanitizer build matrix (#527)
2023-03-26 Stephan WalterFix undefined variables in debug build, remove unused...
2023-03-26 Juan Calderon... Add support for linux/arm64 platform during Docker...
2023-03-26 Stephan WalterUpdate README and comments for standalone perplexity...
2023-03-26 anzz1[main] fix infinite generation (-n == -1) (#523)
2023-03-26 Georgi GerganovAdd logo to README.md
2023-03-26 Harald FernengelExit from interactive mode if input stream is bad ...
2023-03-25 anzz1CI: Run other sanitizer builds even if one fails (...
2023-03-25 jp-x-gClarify console output in convert-pth-to-ggml.py (...
2023-03-25 anzz1CMake / CI additions (#497)
2023-03-25 anzz1(Windows) Set console to UTF-8 on init (#420)
2023-03-25 Georgi GerganovFix colors enabling on WIN32
2023-03-25 Georgi GerganovIf n_predict == -1, generate forever
2023-03-25 Georgi GerganovInifinite generation via context swapping (#71)
2023-03-25 Georgi GerganovCleanup STL headers + fix embedding examples + minor...
2023-03-25 Georgi GerganovMove chat scripts into "./examples"
2023-03-25 slarenAdd AVX2 implementation of dequantize_row_q4_1 (#505)
2023-03-25 Georgi GerganovOverhaul the examples structure
2023-03-25 Georgi GerganovRetire the ggml_mul_mat() branch for transposed src0...
2023-03-25 Georgi GerganovDisable prompt verbosity by default and add option...
2023-03-25 slarenAdd AVX2 implementation of dequantize_row_q4_0 (#467)
2023-03-25 Georgi GerganovDon't interefe with BLAS for large prompts by running...
2023-03-25 Georgi GerganovAdd longer DAN prompt for testing big batch numbers
2023-03-25 slarenAdd timings for the prompt evaluation (#478)
2023-03-25 Georgi GerganovRemove obsolete information from README
2023-03-25 Georgi GerganovRemove obsolete assert and fix compiler warning
2023-03-25 Georgi GerganovFix nasty bug in ggml_compute_forward_mul_mat_f32(...
2023-03-25 anzz1bounds checking for input prefix (#492)
2023-03-25 anzz1feat: '--in-prefix STRING' option (#426)
2023-03-25 Jed FoxAdd support for file load progress reporting callbacks...
2023-03-25 DoomsdayrsAdd missing struct annotation (#483)
2023-03-25 Chris KuehlFix crash for 65B model with pre-allocated memory ...
2023-03-24 Georgi GerganovDisable BLAS altogether - the bug is not just for qunat...
2023-03-24 Georgi GerganovDisable BLAS branch in mul_mat - seems there is a bug
2023-03-24 Georgi GerganovImmediately start processing the prompt before user...
2023-03-24 Georgi GerganovReduce memory usage and allocate enough memory for...
2023-03-24 Georgi GerganovTemporary bump the memory buffer size - hopefully fix...
2023-03-24 Gary MulderUpdate README.md (#444)
2023-03-24 rabidcopyfix instruct mode (#445)
2023-03-24 Georgi GerganovProperly free llama_context on failure
2023-03-24 Cameron Kaiseradditional optimizations for POWER9 (#454)
2023-03-24 comexSupport calling mlock() on loaded model data on Linux...
2023-03-24 LucianoAdd embedding mode with arg flag. Currently working...
2023-03-24 Georgi GerganovAdd link to Roadmap discussion
2023-03-24 Georgi GerganovRevert "Fix memory allocation issues and seg faults"
2023-03-23 Georgi GerganovFix memory allocation issues and seg faults
2023-03-23 Georgi GerganovAvoid the transposed X branch in the Z = X * Y matrix...
2023-03-23 Jed FoxFix quantize script not finding models in parent direct...
2023-03-23 Georgi GerganovRemove oboslete command from Docker script
2023-03-23 Georgi GerganovObsolete
2023-03-23 rabidcopyReplace EOS with newline to prevent context/memory...
2023-03-23 Timmy KnightFix GPTQ converter (#423)
2023-03-23 nusu-githubGenerate library with CMake (#430)
2023-03-23 anzz1Command line args bounds checking (#424)
2023-03-23 Ben SiraphobFix Nix build
2023-03-23 Stephan WalterRevert "Delete SHA256SUMS for now" (#429)
2023-03-23 KerfuffleFix Makefile echo escape codes (by removing them)....
2023-03-23 Gary MulderMove model section from issue template to README.md...
2023-03-23 anzz1Delete SHA256SUMS for now (#416)
2023-03-23 Georgi GerganovAdjust repetition penalty ..
2023-03-23 Georgi GerganovAdd link to recent podcast about whisper.cpp and llama.cpp
2023-03-23 anzz1CI: CMake: Separate build and test steps (#376)
2023-03-23 tjohnmanFix instruct mode broken by PR #354 (#409)
2023-03-22 Gary MulderUpdate issue template so people will use it (#404)
2023-03-22 Stephan WalterDeduplicate q4 quantization functions (#383)
2023-03-22 Valentyn Bezshapkinfix: add POSIX functionality for Linux compilation...
2023-03-22 tjohnmanDon't force immediate interactive without `-i` (#354)
2023-03-22 Erik Scholzcmake: make llama an actual library (#392)
2023-03-22 Erik Scholzfix perplexity after c-api refactor (#390)
2023-03-22 Gary LinscottAdd details on perplexity to README.md (#395)
2023-03-22 Yusuf Kağan... Add missing header for memcpy (#386)
2023-03-22 Georgi GerganovWhen seed <= 0 - use the clock to generate one
next