| .. |
|
backend
|
2d38b6e400
CANN: Add the basic supports of Flash Attention kernel (#13627)
|
vor 8 Monaten |
|
development
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
vor 8 Monaten |
|
multimodal
|
9b61acf060
mtmd : rename llava directory to mtmd (#13311)
|
vor 8 Monaten |
|
android.md
|
68ff663a04
repo : update links to new url (#11886)
|
vor 11 Monaten |
|
build.md
|
84778e9770
CUDA/HIP: Share the same unified memory allocation logic. (#12934)
|
vor 9 Monaten |
|
docker.md
|
33983057d0
musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)
|
vor 8 Monaten |
|
function-calling.md
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
vor 8 Monaten |
|
install.md
|
18b663d8e4
install : add macports (#12518)
|
vor 10 Monaten |
|
llguidance.md
|
89daa2564f
llguidance build fixes for Windows (#11664)
|
vor 11 Monaten |
|
multimodal.md
|
40aaa8a403
mtmd : add support for Qwen2-Audio and SeaLLM-Audio (#13760)
|
vor 8 Monaten |
Bizhao Shi
2d38b6e400
CANN: Add the basic supports of Flash Attention kernel (#13627)