| .. |
|
batched-bench
|
a885dcff11
batched-bench : fix llama_synchronize usage during prompt processing (#15835)
|
hai 4 meses |
|
cvector-generator
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
hai 7 meses |
|
export-lora
|
749e0d27f0
mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503)
|
hai 6 meses |
|
gguf-split
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
imatrix
|
19f68fa5a4
imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076)
|
hai 5 meses |
|
llama-bench
|
360d6533db
ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797)
|
hai 4 meses |
|
main
|
d1c6f11f47
doc : update documentation for --tensor-split (#15980)
|
hai 4 meses |
|
mtmd
|
50f4281a6f
llama : allow using iGPUs with --device (#15951)
|
hai 4 meses |
|
perplexity
|
3ea913f1ce
perplexity: give more information about constraints on failure (#15303)
|
hai 5 meses |
|
quantize
|
fd1234cb46
llama : add gpt-oss (#15091)
|
hai 5 meses |
|
rpc
|
918b26f197
rpc : fix regression when --device is used (#15981)
|
hai 4 meses |
|
run
|
a457551332
cmake : do not search for curl libraries by ourselves (#14613)
|
hai 6 meses |
|
server
|
f088b6a84f
server : adjust prompt similarity thold + add logs (#15913)
|
hai 4 meses |
|
tokenize
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
hai 8 meses |
|
tts
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
hai 4 meses |
|
CMakeLists.txt
|
9b61acf060
mtmd : rename llava directory to mtmd (#13311)
|
hai 8 meses |
Radoslav Gerganov
918b26f197
rpc : fix regression when --device is used (#15981)