vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 15:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Delete unused code

Browse source
This commit is contained in:
Shuaiyi 2025-02-27 13:18:19 +00:00
parent 7a19f3b781
commit a34a25d5cc
1 changed files with 0 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ktransformers/util/utils.py
View file

@ -170,7 +170,6 @@ def prefill_and_generate(model, tokenizer, inputs, max_new_tokens=10000, use_cud
past_key_values.cur_idx=cache_position
start_time = time.time()
inputs_embeds = model.model.embed_tokens(inputs.to("cpu")).to(torch_device)
if mode == "long_context":
inputs_embeds = model.model.embed_tokens(inputs.to("cpu"))
else: