Actions: ggml-org/llama.cpp
Actions
5,217 workflow run results
5,217 workflow run results
max_alloc_size in backend ctx instead of querying again
CI
#20918:
Pull request #12705
opened
by
lhez
server: streaming of tool calls and thoughts when --jinja is on
CI
#20904:
Pull request #12379
synchronize
by
ochafik