LLM inference in C/C++
C++ ggml
Commits on master
ui : fix MCP image attachments not displayed in tool block (#25789) (#28089)
85d5703 nachobh committed 2 months ago
opencl: extend the elementwise and data‐movement op coverage (#27633)
1548a24 Hongqiang Wang committed 2 months ago
ui: export conversations from database instead of cached store (#27432)
1863ac0 Tom Tan committed 2 months ago
model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127)
49c0dc8 HongHuang committed 2 months ago
metal : add remaining fa-vec tunings for M3 Max (#28373)
8f83678 Niklas Wenzel committed 2 months ago
ggml : replace compile definitions with version.h.in (#28364)
86b351f Daniel Bevenius committed 2 months ago
ggml : don't crash when backend search path can't be read (#28271)
4cbe8b0 Adrien Gallouët committed 2 months ago
docs : update maintainer PRs link and regenerate AUTHORS (#28365)
a529af9 Georgi Gerganov committed 2 months ago
vendor: update BoringSSL to 0.20260903.0 (#28354)
38521ec Alessandro de Oliveira Faria (A.K.A.CABELO) committed 2 months ago
common : make build info output stream configurable (#28322)
c390d0a Adrien Gallouët committed 2 months ago
sycl: fuse rms_norm+mul+add and add+add residual chains (#27610)
6703d78 Frosty40 committed 2 months ago
SYCL: Refactor GGML_SYCL_ENABLE_MKL_FA to global var (#26863)
f9f09f0 Ozymandias_EBON committed 2 months ago
llama: fix whole source code rebuilt on each new commit (#28278)
d230ddd Xuan-Son Nguyen committed 2 months ago
common/json-schema : fix GBNF grammar generation for empty object schemas (#28279)
c5a5535 Sergey Sklyarov committed 2 months ago
opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations (speculative decoding/MTP) (#26477)
95ef7fc Hongqiang Wang committed 2 months ago
snapdragon: ci updates to use new run script (#28293)
d30500b Max Krasnyansky committed 2 months ago
ops: add Hexagon to ops.md and update main README.md (#28263)
e107984 Todor Boinovski committed 2 months ago