vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-09 13:55:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix precision bug imported by position_ids in 0.2.0

Browse source
This commit is contained in:
Atream 2025-02-17 09:23:14 +00:00
parent b84524622e
commit 038bc30888
10 changed files with 471 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/operators/linear.py
View file

@ -383,7 +383,7 @@ class KTransformersLinear(BaseInjectedModule, KLinearBase):
prefill_op: str| None = "KLinearTorch",
**kwargs,
):
BaseInjectedModule.__init__(self, key, gguf_loader, config, orig_module, generate_device, **kwargs)
BaseInjectedModule.__init__(self, key, gguf_loader, config, orig_module, prefill_device, generate_device, **kwargs)
KLinearBase.__init__(self, key, gguf_loader, config, orig_module, generate_device, **kwargs)
# build all the linear operators
if prefill_op is not None: