llama-cpp-python
fix: preserve recurrent/hybrid model state when the full prompt is already cached
#2306

Merged

fix: preserve recurrent/hybrid model state when the full prompt is already cached #2306

abetlen merged 1 commit into abetlen:main from allthatido:bugfix/hybrid_model_state_reset

abetlen force pushed from 653d5ddd to 6db27ad6 6 days ago

abetlen force pushed from 6db27ad6 to 47501b21 6 days ago

abetlen force pushed from 47501b21 to f6613308 6 days ago

abetlen force pushed from f6613308 to 8b815f5e 6 days ago

abetlen force pushed from 8b815f5e to ab66b6f6 6 days ago

abetlen force pushed from ab66b6f6 to 173fa12c 5 days ago

abetlen force pushed from 173fa12c to 9b1a645e 5 days ago

abetlen force pushed from 9b1a645e to 0d8ed62b 5 days ago

abetlen force pushed from 0d8ed62b to 57c76838 5 days ago

abetlen force pushed from 57c76838 to 4faeb815 5 days ago

fix: preserve recurrent/hybrid model state when the full prompt is al…

e78de054

abetlen force pushed from 4faeb815 to e78de054 5 days ago

abetlen merged 9be3cd13 into main 5 days ago

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Milestone

No milestone