llama.cpp
Reset schedule earlier to allow overlap with ggml graph computation on device
#6933
Merged

Reset schedule earlier to allow overlap with ggml graph computation on device #6933

agray3
agray3 Reset schedule earlier to allow overlap with graph computation on device
a2beaffe
slaren
sorasoras
agray3 moved reset to end of llama_decode_internal
34847caa
agray3
agray3 agray3 marked this pull request as ready for review 1 year ago
agray3
slaren
slaren commented on 2024-04-26
slaren style fix
728562bc
slaren
slaren approved these changes on 2024-04-26
slaren slaren merged 928e0b70 into master 1 year ago
github-actions

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone