vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 23:34:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

⚡ fix server cache lens

Browse source
This commit is contained in:
liam 2025-03-01 00:09:57 +08:00
parent 71f4599dee
commit 8ddc990668
2 changed files with 10 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ktransformers/server/backend/interfaces/ktransformers.py
View file

@ -130,8 +130,11 @@ class KTransformersInterface(TransformersInterface):
@torch.no_grad
def prefill(self, input_ids: torch.Tensor, is_new: bool):
input_ids_length = input_ids.shape[-1]
if(input_ids_length >= self.args.cache_lens):
logger.warning(f"input_ids_length {input_ids_length} > cache_lens {self.args.cache_lens}")
self.seq_length = input_ids_length
return
logger.debug(f"input_ids: {input_ids.shape}")
device = self.device_map.get("blk.0.self_attn", {}).get("generate_device", "cuda:0")
device = "cuda:0" if device == "cuda" else device