LLM inference in C/C++
C++ ggml
Commits on master
ggml : address integer overflows in binary ops CUDA implementation (#24706)
f728ada fairydreaming committed 4 months ago
ui: fix always-show-sidebar-on-desktop setting after navigation refactor (#24979)
3e61ea0 Pascal committed 4 months ago
tests : synchronize contexts at end of test-thread-safety (#24935)
fdbd6ab Christopher Albert committed 4 months ago
build: include libmtmd in Apple XCFramework (#21935)
e12a012 Abraham Gonzalez committed 4 months ago
hexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled weight repack, kernel-params, cached graphs (#24954)
8be759e Max Krasnyansky committed 4 months ago
mtmd: model: unlimited-ocr: converter + parity test (#24969)
894bb27 Saba Fallah committed 4 months ago
vulkan: allow reducing the graph submission batches to avoid timeouts (#24872)
51eae8c Wagner Bruna committed 4 months ago
vulkan: fail the build when a shader fails to compile (#24450)
1191758 liminfei-amd committed 4 months ago
ui: New Logo + Navigation cleanup & Mobile UI/UX improvements (#24897)
ef9c13d Aleksander Grygier committed 4 months ago
model : Add LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M (#24913)
88636e1 Tarek Dakhran committed 4 months ago
vulkan: Apply bias before softmax in FA, to avoid overflow (#24909)
ac4105d Jeff Bolz committed 4 months ago
vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU/NORM (#24582)
72a9269 Jeff Bolz committed 5 months ago
server: fix remote preset handling, add test (#24938)
75ad0b2 Xuan-Son Nguyen committed 5 months ago
vulkan: link ggml-cpu when GGML_VULKAN_CHECK_RESULTS / RUN_TESTS are enabled (#24444)
c926ad0 Wyatt Caldwell committed 5 months ago
ggml-webgpu: improve MTP inference by using mat-vec path for small batches (#24811)
7c90850 Masashi Yoshimura committed 5 months ago