Michael Yang b323cfe731 gemma2: use fast attention

2025-08-19 13:33:12 -07:00

..

gemma2

gemma2: use fast attention

2025-08-19 13:33:12 -07:00

gemma3

ml: Panic rather than return error on tensor allocation failure

2025-05-22 14:38:09 -07:00

gemma3n

Increase performance for Gemma3n models on NVGPUs by enabling CUDA Graph execution (#11525)

2025-07-29 12:37:06 -07:00

gptoss

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

llama

Only load supported models on new engine (#11362)

2025-07-11 12:21:54 -07:00

llama4

use nn.Linear in place of ml.Tensor (#11049)

2025-06-11 12:10:15 -07:00

mistral3

ml: Panic rather than return error on tensor allocation failure

2025-05-22 14:38:09 -07:00

mllama

ml: Panic rather than return error on tensor allocation failure

2025-05-22 14:38:09 -07:00

qwen2

Only load supported models on new engine (#11362)

2025-07-11 12:21:54 -07:00

qwen3

use nn.Linear in place of ml.Tensor (#11049)

2025-06-11 12:10:15 -07:00

qwen25vl

ml: Panic rather than return error on tensor allocation failure

2025-05-22 14:38:09 -07:00

models.go

gpt-oss (#11672)

2025-08-05 12:21:16 -07:00