ggml : fix ggml_backend_cpu_supports_op() for CPY (llama/0) d645791 ggerganov commited on Apr 21, 2024
ggml : group all experts in a single ggml_mul_mat_id (llama/6505) f0b5c67 slaren ggerganov commited on Apr 18, 2024
fix mul_mat_id() for new input, make the ut pass (llama/6682) 6d1ba81 Neo Zhang Jianyu commited on Apr 15, 2024
fix memcpy() crash, add missed cmd in guide, fix softmax (llama/6622) 6901743 Neo Zhang Jianyu commited on Apr 14, 2024
CUDA: fix matrix multiplication logic for tests (llama/6667) 6ccb5a5 JohannesGaessler commited on Apr 13, 2024
llama : add gguf_remove_key + remove split meta during quantize (llama/6591) 1706870 jiez z5269887 commited on Apr 12, 2024
ggml : expose SSE3 and SSSE3 for MSVC when AVX is available (#2128) 340b9ae unverified Przemysław Pawełczyk commited on May 8, 2024
build : improve disabling AVX-512 (#2129) dd6f1ab unverified Przemysław Pawełczyk commited on May 8, 2024
minor: add CMakeSettings.json to gitignore (#2094) a361a80 unverified stanimirovb commited on May 8, 2024
make : change GNU make default CXX from g++ to c++ (#2100) 610f480 unverified Przemysław Pawełczyk commited on Apr 28, 2024
Remove unnecessary memory reallocation in fft (#2080) 3198674 unverified goldwaving commited on Apr 28, 2024
whisper : more prominent log message for sub-1s audio (#2065) 5ddb20b unverified ggerganov commited on Apr 24, 2024
main : pass nullptr when regex is empty (#2070) 8677fc4 unverified ggerganov commited on Apr 17, 2024
readme : add up-to-date repository for Python bindings (#2063) f573a31 unverified AIWintermuteAI commited on Apr 16, 2024
build : fix embedded Metal library generation (#2045) b0e83a9 unverified Didzis Gosko commited on Apr 15, 2024
build : detect AVX512 in Makefile, add AVX512 option in CMake (#2043) 9d0bb12 unverified Didzis Gosko commited on Apr 15, 2024
whisper.nvim : fix missing reference to "model" variable (#2049) 515c36e unverified sixcircuit commited on Apr 15, 2024
llama : add Command R Plus support (llama/6491) 8cf7097 unverified Carolinabanana S S slaren ggerganov commited on Apr 9, 2024
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (llama/6521) 873102e unverified Neo Zhang Jianyu commited on Apr 7, 2024
common : fix file-handle leak in read_wav() (#2026) ffc6231 unverified ulatekh commited on Apr 9, 2024
main : set stdin to binary mode on Windows (#2025) ed041ef unverified rotemdan commited on Apr 9, 2024
cmake : support for CPU BLAS build via Intel MKL (#2024) 9a2c42b unverified slashlib commited on Apr 9, 2024
main : allow a response-file as the sole parameter (#2019) 07da1b5 unverified ulatekh ggerganov commited on Apr 9, 2024
whisper : suppress tokens with a regex (#1997) 8cc6334 unverified ulatekh ggerganov commited on Apr 9, 2024