Commit Graph

7 Commits

Author SHA1 Message Date
Michael Yang a40d427bce
multi-regexp pretokenizer (#12325) 2025-09-23 13:21:47 -07:00
Michael Yang 564b558c92
fix(llama): other llama flavours (#12308)
* fix(llama): rope scale

* spm llama

* skip moe models

* cleanup
2025-09-17 12:12:21 -07:00
Michael Yang ad95d5b30b
use split activations when possible (#12293)
* use ggml_*_split activations when possible

* forward qkv
2025-09-16 09:51:19 -07:00
Michael Yang 6f7117145f
batch: use tensors for outputs (#12185)
this cleans up the model interface slightly without too much impact in
other areas
2025-09-15 14:33:06 -07:00
Daniel Hiltgen f8a6e88819
Only load supported models on new engine (#11362)
* Only load supported models on new engine

Verify the model is supported before trying to load

* int: testcase for all library models
2025-07-11 12:21:54 -07:00
Jesse Gross 1f371ea92f 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.
2025-05-22 14:38:09 -07:00
Michael Yang c890011322
feat: port qwen2 model (#10782) 2025-05-21 10:21:24 -07:00