| .. |
|
batched-bench
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
cvector-generator
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
export-lora
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
gguf-split
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
imatrix
|
efb8b47eda
imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389)
|
8 months ago |
|
llama-bench
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
8 months ago |
|
main
|
27ebfcacba
llama : do not crash if there is no CPU backend (#13395)
|
8 months ago |
|
mtmd
|
c104023994
mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459)
|
8 months ago |
|
perplexity
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
8 months ago |
|
quantize
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
rpc
|
27ebfcacba
llama : do not crash if there is no CPU backend (#13395)
|
8 months ago |
|
run
|
0527771dd8
llama-run: add support for downloading models from ModelScope (#13370)
|
8 months ago |
|
server
|
9a390c4829
tools : fix uninitialized llama_batch in server (#13436)
|
8 months ago |
|
tokenize
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
tts
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 months ago |
|
CMakeLists.txt
|
9b61acf060
mtmd : rename llava directory to mtmd (#13311)
|
8 months ago |
City
c104023994
mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459)