]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2024-05-14 Georgi Gerganovsync : whisper.cpp
2024-05-14 thewh1teaglewhisper : fix model path encoding in windows (whisper...
2024-05-14 Daniel Ziegenbergmain : dont print timings with --no-prints (whisper...
2024-05-14 Daniel Ziegenbergmain : add options for temperature control (whisper...
2024-05-14 Georgi Gerganovwhisper : switch back to F32 mask (whisper/0)
2024-05-14 mashizoramain : fix double quote escaping in csv output (whisper...
2024-05-14 Georgi Gerganovmetal : tune soft_max number of threads (whisper/0)
2024-05-14 Georgi Gerganovwhisper : remove old flash attn code (whisper/0)
2024-05-14 Georgi Gerganovggml : try fix ppc64 (whisper/0)
2024-05-14 Przemysław... ggml : expose SSE3 and SSSE3 for MSVC when AVX is avail...
2024-05-14 goldwavingRemove unnecessary memory reallocation in fft (whisper...
2024-05-14 Georgi Gerganovwhisper : more prominent log message for sub-1s audio...
2024-05-14 Georgi Gerganovmain : pass nullptr when regex is empty (whisper/2070)
2024-05-14 Ikko Eltociear... whisper : update grammar-parser.cpp (whisper/2058)
2024-05-12 Hong Bo PENGggml : optimize for ppc64le using VSX intrinsics (...
2024-05-11 Georgi Gerganovcuda : remove old alibi sources (#0)
2024-05-11 Georgi Gerganovmetal : fix indent (#0)
2024-05-11 Georgi Gerganovggml : restore sigmoid decl order (#0)
2024-05-11 Georgi Gerganovtests : restore unary tests (#0)
2024-05-11 Georgi Gerganovmnist : clean whitespace
2024-05-11 Georgi Gerganovggml : resolve merge (#0)
2024-05-11 Georgi Gerganovsync : llama.cpp
2024-05-11 Georgi Gerganovggml : full ALiBi support (llama/7192)
2024-05-11 Georgi Gerganovmetal : fix flash attention kernel requirements (llama...
2024-05-11 Ouadie EL FAROUKIMinor arithmetic improvement to mmvq wrapper kernel...
2024-05-11 0cc4mVulkan Bugfixes and Improvements (llama/7084)
2024-05-11 Johannes GäßlerCUDA: generalize FP16 fattn vec kernel (llama/7061)
2024-05-11 Albert Jinopencl : alignment size converted from bits to bytes...
2024-05-11 agray3Introduction of CUDA Graphs to LLama.cpp (llama/6766)
2024-05-11 Gilad Smetal : use `vm_allocate` instead of `posix_memalign...
2024-05-11 Justine Tunneyggml : introduce bfloat16 support (llama/6412)
2024-05-11 Georgi Gerganovmetal : fix unused warning
2024-05-11 William TambelliniAdd an option to build without CUDA VMM (llama/7067)
2024-05-11 Xuan Son Nguyengguf-split: add --no-tensor-first-split (llama/7072)
2024-05-11 Johannes GäßlerCUDA: CUDART < 11.7 workaround for __hmax, __hmax2...
2024-05-11 Kevin Gibbonsswitch to using localizedDescription (llama/7010)
2024-05-11 Georgi Gerganovmetal : remove deprecated error code (llama/7008)
2024-05-11 Kevin Gibbonsmetal : log more info on error (llama/6987)
2024-05-11 Georgi Gerganovggml : add Flash Attention (llama/5021)
2024-05-11 Georgi Gerganovggml : fix __MSC_VER -> _MSC_VER (llama/6977)
2024-05-11 DAN™Fix more int overflow during quant (PPL/CUDA). (llama...
2024-05-11 Xuan Son Nguyengguf : enforce that tensor names are unique (llama...
2024-05-11 Neo Zhangadd device version in device list (llama/6959)
2024-05-11 agray3Reset schedule earlier to allow overlap with ggml graph...
2024-05-11 slarenadd basic tensor data validation function (llama/6884)
2024-05-11 slarengguf : fix mismatch between alloc and free functions...
2024-05-11 Georgi GerganovMerge pull request from GHSA-p5mv-gjc5-mwqv
2024-05-11 Georgi Gerganovggml : fix redefinition of vaddvq_f32 for 32-bit ARM...
2024-05-11 Georgi Gerganovggml : fix MIN / MAX macros (llama/6904)
2024-05-11 Georgi Gerganovggml : move 32-bit arm compat in ggml-impl.h (llama...
2024-05-11 Justine Tunneyllamafile : improve sgemm.cpp (llama/6796)
2024-05-11 Dave Airlieggml : fix calloc argument ordering. (llama/6820)
2024-05-11 Georgi Gerganovggml : fix ggml_backend_cpu_supports_op() for CPY ...
2024-05-11 slarenggml : group all experts in a single ggml_mul_mat_id...
2024-05-11 Georgi Gerganovggml : fix llamafile sgemm wdata offsets (llama/6710)
2024-05-11 Justine Tunneyggml : add llamafile sgemm (llama/6414)
2024-05-11 Shijiellama : add qwen2moe (llama/6074)
2024-05-11 Neo Zhang Jianyufix mul_mat_id() for new input, make the ut pass (llama...
2024-05-11 DaveAdded support for GGML_OP_CLAMP in Metal (llama/6662)
2024-05-11 Neo Zhang Jianyufix memcpy() crash, add missed cmd in guide, fix softma...
2024-05-11 Johannes GäßlerCUDA: fix matrix multiplication logic for tests (llama...
2024-05-11 slarenmetal : unify mul_mv_id kernels (llama/6556)
2024-05-11 jiezllama : add gguf_remove_key + remove split meta during...
2024-05-01 Justina Chofeat: implemented sigmoid function (#806)
2024-04-25 Borislav Stanimirovbuild: fix and ignore msvc warnings (#805)
2024-04-18 Daniel Beveniusspec : fix typo in gguf.md (#798)
2024-04-09 Georgi Gerganovsync : whisper.cpp
2024-04-09 Brad Murraywhisper : fix DTW memory access (whisper/2012)
2024-04-09 ulatekhcommon : fix file-handle leak in read_wav() (whisper...
2024-04-09 Rotem Danmain : set stdin to binary mode on Windows (whisper...
2024-04-09 ulatekhmain : allow a response-file as the sole parameter...
2024-04-09 ulatekhwhisper : suppress tokens with a regex (whisper/1997)
2024-04-09 Georgi Gerganovsync : llama.cpp
2024-04-09 Georgi Gerganovlicense : update copyright notice + add AUTHORS
2024-04-09 Carolinabananallama : add Command R Plus support (llama/6491)
2024-04-09 Abhilash Majumderremove row=1 cond (llama/6532)
2024-04-09 Neo Zhang Jianyusupport/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS...
2024-04-09 Georgi Gerganovscripts : sync LICENSE and gen-authors.sh
2024-04-07 Georgi Gerganovsync : whisper.cpp (grammar-parser, skip)
2024-04-07 Georgi Gerganovsync : whisper.cpp
2024-04-07 Slava Primenkoggml: bypass code incompatible with CUDA < 11.1 (whispe...
2024-04-07 ulatekhmain : add command-style grammar (whisper/1998)
2024-04-07 Georgi Gerganovscripts : sync ggml-cuda folder
2024-04-06 Georgi Gerganovci : temporary build embeded metal library
2024-04-06 Georgi Gerganovsync : llama.cpp (skip)
2024-04-06 Ouadie EL FAROUKIFixed minor bug when enabling FP16 for non intel target...
2024-04-06 slarenggml : mul_mat_id use the same tensor for all the exper...
2024-04-06 Meng, HengyuDisable iqx on windows as WA (llama/6435)
2024-04-06 0cc4mVulkan k-quant mmq and ggml-backend offload functionali...
2024-04-06 Neo Zhang Jianyufix set main gpu crash (llama/6339)
2024-04-06 slarenggml : fix bounds checking of zero size views (llama...
2024-04-03 Daniel Beveniusbackend : fix typo in scheduler documentation (#781)
2024-04-03 Andreicmake : add `GGML_METAL_EMBED_LIBRARY` (#780)
2024-04-03 Georgi Gerganovlogo : add files (#782)
2024-03-27 JacobLinCoolgguf : update type enum (#775)
2024-03-27 Georgi Gerganovsync : whisper.cpp
2024-03-27 Georgi Gerganovsync : whisper.cpp
2024-03-27 Georgi Gerganovwhisper : improve handling of prompts (whisper/1981)
2024-03-27 Sanchit Gandhiwhisper : improve support for distil-large-v3 (whisper...
2024-03-27 denerscwhisper : token-level timestamps with DTW (whisper...
next