LLM inference in C/C++
C++ ggml
Commits on master
ggml : add a set of functions for checking contiguity of inner tensor dimensions (#25650)
a7312ae fairydreaming committed 4 months ago
tests: export-graph-ops: exit gracefully when called w/o arguments (#25619)
657e011 Christian Kastner committed 4 months ago
convert_hf_to_gguf: support split MTP export for HY V3 (#25641)
cb489bc Thiago Padilha committed 4 months ago
arg: Flush log before exiting after usage() (#25504)
ec0dbef Christian Kastner committed 4 months ago
sycl: set fattn_vec_nthreads to 256 for Battlemage (#25205)
c1063ac Titaniumtown committed 4 months ago
model: add Hy3 (hy_v3) support with MTP speculative decoding (#25395)
2969d6d Satinder Grewal committed 4 months ago
vulkan: Use native e2m1 and e4m3 conversions for mxfp4/nvfp4 (#25338)
e920c52 Jeff Bolz committed 4 months ago
chat : fix reasoning leak with force-opened bare <think> templates (#24674)
91c631b Frosty40 committed 4 months ago
ui: Remove recommended MCP Servers + improve MCP Servers Settings UI/UX (#25535)
38fd5c9 Aleksander Grygier committed 4 months ago
server: honour per-request reasoning_budget_tokens in chat completions (#23116)
99f3dc3 Bernard Ladenthin committed 4 months ago
vendor : update cpp-httplib to 0.50.1 (#25576)
3455882 Alessandro de Oliveira Faria (A.K.A.CABELO) committed 4 months ago
server: Don't consider models with --no-mmproj-auto as multimodal (#25590)
8014d2c Sebastian Dröge committed 4 months ago
server : evict checkpoints within min-step of each other (#25472)
0c4fa7a Aldehir Rojas committed 4 months ago
server : fix image blocks in tool_result being dropped during Anthropic OpenAI conversion (#22536)
6b4dc21 quei committed 4 months ago
Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR not implemented for architecture' message (#24926)
e3546c7 kdkd committed 4 months ago