[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-09-24 14:14:10 +00:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 484c211fe8
commit d881812500
218 changed files with 869 additions and 813 deletions
+2 -2
View File
@@ -164,9 +164,9 @@ For your model to be compatible with vLLM's tensor parallel and/or pipeline para
```python
from transformers import PretrainedConfig
from transformers import PreTrainedConfig
class MyConfig(PretrainedConfig):
class MyConfig(PreTrainedConfig):
base_model_tp_plan = {
"layers.*.self_attn.k_proj": "colwise",
"layers.*.self_attn.v_proj": "colwise",