City c104023994 mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459)		2025-05-12 00:39:06 +02:00
..
batched-bench
cvector-generator
export-lora
gguf-split
imatrix
llama-bench	Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B (#13386)	2025-05-11 14:18:39 +02:00
main
mtmd	mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459)	2025-05-12 00:39:06 +02:00
perplexity
quantize
rpc
run
server	tools : fix uninitialized llama_batch in server (#13436)	2025-05-11 17:08:26 +02:00
tokenize
tts
CMakeLists.txt