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 #10236] Send Multiple Chat Requests to Ollama Server Does Not Work #68775

New Issue
Closed
opened 2026-05-04 15:09:28 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 15:09:28 -05:00
Owner
Copy Link

Originally created by @JasonHonKL on GitHub (Apr 11, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10236

What is the issue?

Image

When I send 5 post requests to Ollama, the first request would work and others won't. I am currently using Mac book M1. This maybe an issue as using GPU seems work. To reproduce the bug you just need to send five curl hello world to deepseek-r1:8b model at the same time you should be able to reproduce the bug. Thanks a lot !

Relevant log output

[GIN] 2025/04/12 - 02:29:08 | 200 |         1m36s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/04/12 - 02:29:08 | 500 |         1m36s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/04/12 - 02:29:08 | 500 |         1m36s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/04/12 - 02:29:08 | 500 |         1m36s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/04/12 - 02:29:08 | 500 |         1m36s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/04/12 - 02:29:08 | 500 |         1m36s |       127.0.0.1 | POST     "/api/chat"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

latest (git repo main)

Originally created by @JasonHonKL on GitHub (Apr 11, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10236 ### What is the issue? <img width="997" alt="Image" src="https://github.com/user-attachments/assets/952eecac-6942-4ea4-a7a5-6af26c8fb84e" /> When I send 5 post requests to Ollama, the first request would work and others won't. I am currently using Mac book M1. This maybe an issue as using GPU seems work. To reproduce the bug you just need to send five curl hello world to deepseek-r1:8b model at the same time you should be able to reproduce the bug. Thanks a lot ! ### Relevant log output ```shell [GIN] 2025/04/12 - 02:29:08 | 200 | 1m36s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/04/12 - 02:29:08 | 500 | 1m36s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/04/12 - 02:29:08 | 500 | 1m36s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/04/12 - 02:29:08 | 500 | 1m36s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/04/12 - 02:29:08 | 500 | 1m36s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/04/12 - 02:29:08 | 500 | 1m36s | 127.0.0.1 | POST "/api/chat" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version latest (git repo main)
GiteaMirror added the bug label 2026-05-04 15:09:28 -05:00
GiteaMirror commented 2026-05-04 15:09:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 11, 2025):

Full server log will make it easier to diagnose. Can you show the prompt and the mechanism for submitting simultaneous prompts?

<!-- gh-comment-id:2797794745 --> @rick-github commented on GitHub (Apr 11, 2025): Full server log will make it easier to diagnose. Can you show the prompt and the mechanism for submitting simultaneous prompts?
GiteaMirror commented 2026-05-04 15:09:39 -05:00
Author
Owner
Copy Link

@JasonHonKL commented on GitHub (Apr 12, 2025):

@rick-github Sorry for forgetting to post my server log. Here's the log

panic unable to load model: [File Directory of the model]
goroutine 5 [running]:
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0x1400014a2d0, {0x1b, 0x0, 0x1, 0x0
, {0x0, 0x0, 0x0}, 0x14000047c00, 0x0}, ...)
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:851 +0x2c8
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:966 +0xa50
time=2025-03-13T16:36:19.825+08:00 level=ERROR source=server.go:421 msg="llama runner terminated" error="exit status 2"
time=2025-03-13T16:36:19.831+08:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade"
[GIN] 2025/03/13 - 16:36:19 | 500 |  646.450041ms |       127.0.0.1 | POST     "/api/generate"

However the first request works. i.e the model exists and work for the first request.
Here's the prompt

	prompt := "Please summarize the following content of the file. Highlight the main ideas, key points, and any important details. Here is the content: \n" + fileContent + "\nMake sure to provide a concise yet comprehensive summary. Ensure the agent response is in JSON format with the summary as \"summary\":summary."

I use go routine to send 5 request to Ollama server with \chat api. Thanks a lot.

<!-- gh-comment-id:2798407359 --> @JasonHonKL commented on GitHub (Apr 12, 2025): @rick-github Sorry for forgetting to post my server log. Here's the log ``` panic unable to load model: [File Directory of the model] goroutine 5 [running]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0x1400014a2d0, {0x1b, 0x0, 0x1, 0x0 , {0x0, 0x0, 0x0}, 0x14000047c00, 0x0}, ...) /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:851 +0x2c8 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:966 +0xa50 time=2025-03-13T16:36:19.825+08:00 level=ERROR source=server.go:421 msg="llama runner terminated" error="exit status 2" time=2025-03-13T16:36:19.831+08:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade" [GIN] 2025/03/13 - 16:36:19 | 500 | 646.450041ms | 127.0.0.1 | POST "/api/generate" ``` However the first request works. i.e the model exists and work for the first request. Here's the prompt ```go prompt := "Please summarize the following content of the file. Highlight the main ideas, key points, and any important details. Here is the content: \n" + fileContent + "\nMake sure to provide a concise yet comprehensive summary. Ensure the agent response is in JSON format with the summary as \"summary\":summary." ``` I use go routine to send 5 request to Ollama server with \chat api. Thanks a lot.
GiteaMirror commented 2026-05-04 15:09:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 12, 2025):

Full server log will make it easier to diagnose.

<!-- gh-comment-id:2798758151 --> @rick-github commented on GitHub (Apr 12, 2025): **Full** server log will make it easier to diagnose.
GiteaMirror commented 2026-05-04 15:09:46 -05:00
Author
Owner
Copy Link

@JasonHonKL commented on GitHub (Apr 13, 2025):

Thanks I just solved. I forget to set max no. of worker with my old computer. Sorry for bothering.

<!-- gh-comment-id:2799594987 --> @JasonHonKL commented on GitHub (Apr 13, 2025): Thanks I just solved. I forget to set max no. of worker with my old computer. Sorry for bothering.
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
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#68775
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?