Add StreamingLLM for llamacpp & llamacpp_HF (2nd attempt) (#5669)

This commit is contained in:
oobabooga 2024-03-09 00:25:33 -03:00 committed by GitHub
parent 9271e80914
commit afb51bd5d6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 147 additions and 0 deletions

View file

@ -46,6 +46,8 @@ loaders_and_params = OrderedDict({
'no_offload_kqv',
'row_split',
'tensorcores',
'streaming_llm',
'attention_sink_size',
],
'llamacpp_HF': [
'n_ctx',
@ -69,6 +71,8 @@ loaders_and_params = OrderedDict({
'no_offload_kqv',
'row_split',
'tensorcores',
'streaming_llm',
'attention_sink_size',
'llamacpp_HF_info',
],
'ExLlamav2_HF': [