llama.cpp
ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH
#18535
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH
#18535
ggerganov
merged 5 commits into
ggml-org:master
from
DocShotgun:op-offload-min-batch
ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH
3c1bcf26
DocShotgun
requested a review
from
0cc4m
34 days ago
DocShotgun
requested a review
from
ggerganov
34 days ago
github-actions
added
Nvidia GPU
github-actions
added
Vulkan
github-actions
added
ggml
github-actions
added
SYCL
github-actions
added
Apple Metal
github-actions
added
Ascend NPU
ggerganov
commented on 2026-01-02
ggml: read GGML_OP_OFFLOAD_MIN_BATCH once and store to dev ctx
fa467740
cann: forward declaration of device context struct
a449358f
cann: move offload op check after device context declaration
7a838e78
NeoZhangJianyu
commented on 2026-01-04
am17an
approved these changes on 2026-01-06
cuda: fix whitespace
919aa4f9
ggerganov
merged
9a5724de
into master
28 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
am17an
NeoZhangJianyu
ggerganov
0cc4m
Assignees
No one assigned
Labels
Nvidia GPU
Vulkan
ggml
SYCL
Apple Metal
Ascend NPU
Milestone
No milestone
Login to write a write a comment.
Login via GitHub