llama.cpp
ggml : unify rope norm/neox
#7634
Merged

ggml : unify rope norm/neox #7634

ggerganov merged 9 commits into master from gg/rope-refactor
ggerganov
github-actions github-actions added ggml
li-plus
github-actions
ggerganov ggerganov changed the title ggml : unify rope norm/neox (CPU) ggml : unify rope norm/neox 1 year ago
ggerganov ggerganov force pushed 1 year ago
github-actions github-actions added testing
github-actions github-actions added Nvidia GPU
github-actions github-actions added Vulkan
github-actions github-actions added examples
github-actions github-actions added SYCL
ggerganov ggerganov marked this pull request as ready for review 1 year ago
github-actions github-actions added python
github-actions github-actions added Kompute
ggerganov ggerganov force pushed to 6ebee167 1 year ago
mofosyne mofosyne added Review Complexity : High
mofosyne mofosyne added refactoring
mofosyne mofosyne requested a review from slaren slaren 1 year ago
mofosyne mofosyne requested a review from xaedes xaedes 1 year ago
slaren
slaren commented on 2024-06-02
ggerganov ggml : unify rope norm/neox (CPU)
2fd31fe1
ggerganov ggml : fix compile warning
e2370c8e
ggerganov ggml : remove GLM rope mode
cbe4f5f7
ggerganov metal : better rope implementation
3035c2db
ggerganov cuda : better rope implementation
c989fd06
ggerganov naming : n_orig_ctx -> n_ctx_orig
572446bf
ggerganov dev : add reminders to update backends
437d2d60
ggerganov vulkan : fix ggml_rope_ext() usage
61e0a84f
ggerganov cuda : fix array size + indents
ddac1ef6
ggerganov ggerganov force pushed to ddac1ef6 1 year ago
ggerganov ggerganov merged 2b338967 into master 1 year ago
ggerganov ggerganov deleted the gg/rope-refactor branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone