biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Raise error when using encoder/decoder model with cpu backend (#8355)

Browse Source
This commit is contained in:
Kevin Lin
2024-09-12 00:45:24 -05:00
committed by GitHub
parent 1bf2dd9df0
commit 295c4730a8
2 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/utils.py
View File

@@ -82,6 +82,9 @@ STR_NOT_IMPL_ENC_DEC_PROMPT_ADAPTER = ("Prompt adapters are not "
"currently supported with encoder/"
"decoder models.")
STR_NOT_IMPL_ENC_DEC_CPU = ("CPU is not currently supported with "
"encoder/decoder models.")
# Efficiently import all enc/dec error strings
# rather than having to import all of the above
STR_NOT_IMPL_ENC_DEC_ERR_STRS = {
@@ -97,6 +100,7 @@ STR_NOT_IMPL_ENC_DEC_ERR_STRS = {
"STR_NOT_IMPL_ENC_DEC_CUDA_GRAPH": STR_NOT_IMPL_ENC_DEC_CUDAGRAPH,
"STR_NOT_IMPL_ENC_DEC_BACKEND": STR_NOT_IMPL_ENC_DEC_BACKEND,
"STR_NOT_IMPL_ENC_DEC_PROMPT_ADAPTER": STR_NOT_IMPL_ENC_DEC_PROMPT_ADAPTER,
"STR_NOT_IMPL_ENC_DEC_CPU": STR_NOT_IMPL_ENC_DEC_CPU
}
# Constants related to forcing the attention backend selection