llama.cpp
supports running on CPU for GGML_USE_CUBLAS=ON build
#3946

Merged

supports running on CPU for GGML_USE_CUBLAS=ON build #3946

ggerganov merged 3 commits into ggml-org:master from TabbyML:support-cuda-separate-init

wsxiaoys marked this pull request as draft 2 years ago

cebtenzzre commented on 2023-11-04

wsxiaoys changed the title ~~Prototyping the idea that supports running on CPU for a GGML_USE_CUBLAS=on build~~ Prototyping the idea that supports running on CPU for a GGML_USE_CUBLAS=ON build 2 years ago

wsxiaoys force pushed from 1149f4bf to 1caf0c4b 2 years ago

wsxiaoys force pushed from 1caf0c4b to 1a1ffd47 2 years ago

wsxiaoys marked this pull request as ready for review 2 years ago

wsxiaoys changed the title ~~Prototyping the idea that supports running on CPU for a GGML_USE_CUBLAS=ON build~~ supports running on CPU for GGML_USE_CUBLAS=ON build 2 years ago

ggerganov added need feedback

slaren commented on 2023-11-05

wsxiaoys force pushed from 32f07ea6 to 42e642a1 2 years ago

wsxiaoys force pushed from 9c655dcd to b66fdd11 2 years ago

protyping the idea that supports running on CPU for a GGML_USE_CUBLAS…

c58e809c

wsxiaoys force pushed from b66fdd11 to c58e809c 2 years ago

ggerganov commented on 2023-11-06

ggerganov approved these changes on 2023-11-06

doc: add comments to ggml_cublas_loaded()

fe381b06

ggerganov requested a review from

slaren 2 years ago

slaren commented on 2023-11-06

fix defined(...)

fa234945

slaren approved these changes on 2023-11-06

ggerganov merged 46876d2a into master 2 years ago

Reviewers

slaren

ggerganov

cebtenzzre

Assignees

No one assigned

Labels

need feedback

Milestone

No milestone

llama.cpp supports running on CPU for GGML_USE_CUBLAS=ON build #3946 Merged

supports running on CPU for GGML_USE_CUBLAS=ON build #3946

llama.cpp
supports running on CPU for GGML_USE_CUBLAS=ON build
#3946

Merged