parakon-runtime / conversion

1 MB

Ctrl+K

1 contributor

History: 2 commits

kat0012

Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2)

2b12537 verified 15 days ago

__init__.py
15.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
afmoe.py
3.23 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
arctic.py
6.87 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
baichuan.py
2.55 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
bailingmoe.py
9.48 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
bailingmoe3.py
9.08 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
base.py
145 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
bert.py
27.5 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
bitnet.py
1.88 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
bloom.py
2.98 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
chameleon.py
2.44 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
chatglm.py
8.44 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
codeshell.py
1.02 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
cogvlm.py
1.09 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
command_r.py
8.19 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
dbrx.py
3.69 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
deci.py
9.38 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
deepseek.py
51.5 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
dots1.py
1.2 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
dots3.py
16.9 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
dotsocr.py
2.14 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
dream.py
2.91 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
ernie.py
8.84 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
exaone.py
15.3 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
falcon.py
2.75 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
falcon_h1.py
5.51 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
gemma.py
50.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
glm.py
18.4 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
gpt2.py
3.32 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
gpt_oss.py
5.98 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
gptneox.py
2.95 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
granite.py
38.6 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
grok.py
5.2 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
grovemoe.py
4.86 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
hunyuan.py
22.9 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
hy_v4.py
11.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
internlm.py
11 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
internvl.py
4.52 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
jais.py
4.18 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
jamba.py
5.06 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
januspro.py
4.39 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
kimi_k3.py
18.1 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
kimi_linear.py
11.7 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels 15 days ago
kimivl.py
7.82 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago
laguna.py
10.6 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago
lfm2.py
10.7 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago
lighton_ocr.py
933 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago
llada.py
7.13 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago
llama.py
21.4 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago
llama4.py
1.71 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 2) 15 days ago