LLM inference in C/C++
C++ ggml
Commits on master
ci : fix dry-run reporting in make-release job [no ci] (#27167)
4df29be Daniel Bevenius committed 3 months ago
chat: refactor handling supports_string_content / supports_typed_content (#27130)
b94041a Xuan-Son Nguyen committed 3 months ago
llama : check LoRA tensor data is within file bounds (#27056)
10bf611 Oğuzhan Akkaya committed 3 months ago
ui: mask API Key field in settings and error splash to stop browser a… (#26562)
ece963f Cristiano Pinto committed 3 months ago
ui: read structuredContent from MCP tool result when content is empty (#26691)
0d9ceae Gautam0507 committed 3 months ago
server: re-design yield_to_queue thread model (#27133)
22b8e31 Xuan-Son Nguyen committed 3 months ago
vendor: update BoringSSL to 0.20260813.0 (#27099)
adb55e5 Alessandro de Oliveira Faria (A.K.A.CABELO) committed 3 months ago
vendor : update cpp-httplib to 0.53.1 (#27103)
77140d2 Alessandro de Oliveira Faria (A.K.A.CABELO) committed 3 months ago
common: support --models-dir loading MTP assistant models (#24431)
5f754ea Eric Zhang committed 3 months ago
vulkan: add SHMEM_STRIDE_PAD/APPLY_SLM_A_RESHAPE for coopmat1 on Intel Xe (#25380)
9b0a2ce Jiang, Fish committed 3 months ago
common: migrate the deprecated --mmap/--no-mmap to --load-mode (#26934)
0177dcc Fathi Boudra committed 3 months ago
Fixed gating logic for problematic Intel driver version
7b38cb7 Masato Nakasaka committed 3 months ago
mtmd: fix Granite4 Vision image sequence assembly (#26653)
9d57ce4 Hemanth Battu committed 3 months ago
model : add support for MiniMaxText01ForCausalLM and MiniMaxM1ForCausalLM (#27018)
16d222f fairydreaming committed 3 months ago
server: allow accessing /metrics and /slots during llama_decode() (#27041)
77918ca Xuan-Son Nguyen committed 3 months ago
tests : replace personal home directory paths with generic placeholders (#27043)
885c5bb Jim Wu committed 3 months ago
sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779)
6509138 Titaniumtown committed 3 months ago