llama.cpp
f015b266 - llama : more robust cell_max heuristic + wip shift

Commit

2 years ago

llama : more robust cell_max heuristic + wip shift

References

#3228 - llama : custom attention mask + parallel decoding + no context swaps

Author

ggerganov

ggerganov

Committer

ggerganov

ggerganov

Parents

Loading