ollama/model/models
Jesse Gross d1ed4b17ef
ml: Panic rather than return error on tensor allocation failure
FromFloatSlice and FromIntSlice return an error if the shape doesn't
match the passed data or if memory can't be allocated. Since these
are inputs, the memory being allocated is system memory rather than VRAM.

In many cases, the caller can't really handle the error and panics.

Empty and Zeros directly panic if they can't allocate memory.

This makes things consistent by panicing for the first two cases,
removing a fair amount of error handling code. This is also consistent
with how Go typically handles these situations.
2025-12-29 06:38:06 -06:00
..
gemma2 ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
gemma3 ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
llama ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
llama4 ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
mistral3 ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
mllama ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
qwen2 ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
qwen3 ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
qwen25vl ml: Panic rather than return error on tensor allocation failure 2025-12-29 06:38:06 -06:00
models.go feat: port qwen2 model (#10782) 2025-12-29 06:38:04 -06:00