github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6437] how to use batch when using llm #50558

New Issue
Open
opened 2026-04-28 16:23:23 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 16:23:23 -05:00
Owner
Copy Link

Originally created by @PassStory on GitHub (Aug 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6437

I noticed the api does not support processing batch prompt, the GPU utilization is low, and i want to use batch mode to improve GPU utilization and accelerate the inference process, so, how to do that

Originally created by @PassStory on GitHub (Aug 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6437 I noticed the api does not support processing batch prompt, the GPU utilization is low, and i want to use batch mode to improve GPU utilization and accelerate the inference process, so, how to do that
GiteaMirror added the feature request label 2026-04-28 16:23:23 -05:00
GiteaMirror commented 2026-04-28 16:23:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 20, 2024):

#!/bin/bash

[ -z "$1" ] && { echo "usage: $0 batch-file" ; exit 1 ; }

export OLLAMA_HOST=${OLLAMA_HOST-localhost:11434}

get_completion() {
  id="$(jq -r .custom_id <<< "$1")"
  url="$(jq -r .url <<< "$1")"
  body="$(jq -cr .body <<< "$1")"
  curl -s $OLLAMA_HOST$url -d "$body" | jq -c '{"custom_id":"'$id'"}+.'
}
export -f get_completion

parallel --jobs ${OLLAMA_NUM_PARALLEL-1} get_completion < "$1"
<!-- gh-comment-id:2299259065 --> @rick-github commented on GitHub (Aug 20, 2024): ```bash #!/bin/bash [ -z "$1" ] && { echo "usage: $0 batch-file" ; exit 1 ; } export OLLAMA_HOST=${OLLAMA_HOST-localhost:11434} get_completion() { id="$(jq -r .custom_id <<< "$1")" url="$(jq -r .url <<< "$1")" body="$(jq -cr .body <<< "$1")" curl -s $OLLAMA_HOST$url -d "$body" | jq -c '{"custom_id":"'$id'"}+.' } export -f get_completion parallel --jobs ${OLLAMA_NUM_PARALLEL-1} get_completion < "$1" ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#50558
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?