github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5400] Gemma2 work incorrect in parallel request #3380

New Issue
Closed
opened 2026-04-12 14:00:50 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 14:00:50 -05:00
Owner
Copy Link

Originally created by @dooezgo on GitHub (Jul 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5400

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I'm testing for the multiple requests that can be handled in my system.
For Gemma2, when executing a single request, the respond is perfect.
But for multiple requests, the response looks so dummy.
image
I tried multi-request with llama3 but it worked perfectly on that.

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

v0.1.48

Originally created by @dooezgo on GitHub (Jul 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5400 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I'm testing for the multiple requests that can be handled in my system. For Gemma2, when executing a single request, the respond is perfect. But for multiple requests, the response looks so dummy. ![image](https://github.com/ollama/ollama/assets/33556384/3bdbbf5a-264e-4ba8-8f00-b6f3ea31f780) I tried multi-request with llama3 but it worked perfectly on that. ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version v0.1.48
GiteaMirror added the needs more infobug labels 2026-04-12 14:00:50 -05:00
GiteaMirror commented 2026-04-12 14:00:53 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 24, 2024):

I'm not able to reproduce. On a GPU where the model fully loads into VRAM, sending parallel requests doesn't result in gibberish responses.

Can you share more information about your setup? Is the model split between GPU/CPU? How much VRAM do you have?

<!-- gh-comment-id:2248693675 --> @dhiltgen commented on GitHub (Jul 24, 2024): I'm not able to reproduce. On a GPU where the model fully loads into VRAM, sending parallel requests doesn't result in gibberish responses. Can you share more information about your setup? Is the model split between GPU/CPU? How much VRAM do you have?
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 bug needs more info
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#3380
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?