llama.cpp
CUDA memory pool with async memory allocation/deallocation
#3903
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
3
Changes
View On
GitHub
CUDA memory pool with async memory allocation/deallocation
#3903
ggerganov
merged 3 commits into
ggml-org:master
from
young-developer:cuda-memory-pool
Using cuda memory pools for async alloc/dealloc.
08868a44
If cuda device doesnt support memory pool than use old implementation.
7e6f4132
young-developer
changed the title
CUDA memory pool with async memory allocation deallocation
CUDA memory pool with async memory allocation/deallocation
1 year ago
slaren
commented on 2023-11-02
Removed redundant cublasSetStream
587ff3bf
slaren
approved these changes on 2023-11-02
ggerganov
approved these changes on 2023-11-02
ggerganov
merged
d6069051
into master
1 year ago
young-developer
deleted the cuda-memory-pool branch
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
slaren
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub