ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

fix conflict with quant kv (#11737)

Browse source
This commit is contained in:
Yina Chen 2024-08-07 13:10:30 +03:00 committed by GitHub
parent 00a5574c8a
commit e956e71fc1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
python/llm/src/ipex_llm/transformers/models/qwen2.py
View file

@ -123,7 +123,7 @@ def qwen2_model_forward(
if use_cache: if use_cache:
if use_quantize_kv and not isinstance(past_key_values, DynamicFp8Cache): if use_quantize_kv and not isinstance(past_key_values, DynamicFp8Cache):
past_key_values = DynamicFp8Cache.from_legacy_cache(past_key_values) past_key_values = DynamicFp8Cache.from_legacy_cache(past_key_values)
elif use_compress_kv and not isinstance(past_key_values, elif not use_quantize_kv and use_compress_kv and not isinstance(past_key_values,
DynamicCompressCache): DynamicCompressCache):
past_key_values = DynamicCompressCache.from_legacy_cache(past_key_values) past_key_values = DynamicCompressCache.from_legacy_cache(past_key_values)
if not use_quantize_kv and not use_compress_kv and not isinstance(past_key_values, if not use_quantize_kv and not use_compress_kv and not isinstance(past_key_values,