github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7617] llama3.2-vision #30620

New Issue
Closed
opened 2026-04-22 10:26:50 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 10:26:50 -05:00
Owner
Copy Link

Originally created by @tonilampela on GitHub (Nov 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7617

What is the issue?

Running llama3.2-vision 11b model currently seem to throw request timed out errors.

BoltAI 1.26.1
ollama 0.4.1

In ollama console output I can see:

[GIN] 2024/11/11 - 10:17:38 | 500 |          1m0s |       127.0.0.1 | POST     "/v1/chat/completions"
time=2024-11-11T10:17:38.719+02:00 level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.4.1

Originally created by @tonilampela on GitHub (Nov 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7617 ### What is the issue? Running llama3.2-vision 11b model currently seem to throw request timed out errors. BoltAI 1.26.1 ollama 0.4.1 In ollama console output I can see: ``` [GIN] 2024/11/11 - 10:17:38 | 500 | 1m0s | 127.0.0.1 | POST "/v1/chat/completions" time=2024-11-11T10:17:38.719+02:00 level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.4.1
GiteaMirror added the bug label 2026-04-22 10:26:50 -05:00
GiteaMirror commented 2026-04-22 10:26:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 11, 2024):

Your client has a 1 minute timeout.

<!-- gh-comment-id:2467716637 --> @rick-github commented on GitHub (Nov 11, 2024): Your client has a 1 minute timeout.
GiteaMirror commented 2026-04-22 10:26:53 -05:00
Author
Owner
Copy Link

@tonilampela commented on GitHub (Nov 11, 2024):

Your client has a 1 minute timeout.

Yeah, I found from advanced settings timeout adjustment and that seemed to sort it. Thanks!

<!-- gh-comment-id:2468124734 --> @tonilampela commented on GitHub (Nov 11, 2024): > Your client has a 1 minute timeout. Yeah, I found from advanced settings timeout adjustment and that seemed to sort it. Thanks!
GiteaMirror commented 2026-04-22 10:26:54 -05:00
Author
Owner
Copy Link

@maxi1134 commented on GitHub (Nov 25, 2024):

I too get "msg="mllama doesn't support parallel requests yet"".

Yet I have no error 500 indicating a timeout.

Could it be something else?

I am on v0.4.4

equests yet"
Nov 25 14:53:48 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:53:48 | 200 |   2.12196848s |    192.168.0.15 | POST     "/api/generate"
Nov 25 14:54:16 machinelearning ollama[586]: time=2024-11-25T14:54:16.635Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:54:27 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:54:27 | 200 | 10.976419175s |    192.168.0.15 | POST     "/api/generate"
Nov 25 14:54:28 machinelearning ollama[586]: time=2024-11-25T14:54:28.514Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:54:29 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:54:29 | 200 |  526.881149ms |    192.168.0.15 | POST     "/api/generate"
Nov 25 14:55:22 machinelearning ollama[586]: time=2024-11-25T14:55:22.022Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:55:33 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:55:33 | 200 | 11.142031778s |    192.168.0.15 | POST     "/api/generate"
Nov 25 14:55:33 machinelearning ollama[586]: time=2024-11-25T14:55:33.167Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:55:34 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:55:34 | 200 |  1.591731104s |    192.168.0.15 | POST     "/api/generate"
Nov 25 14:58:26 machinelearning ollama[586]: time=2024-11-25T14:58:26.031Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:58:26 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:58:26 | 200 |   18.326325ms |             ::1 | POST     "/api/generate"
Nov 25 14:59:01 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:01 | 200 |      39.301µs |       127.0.0.1 | HEAD     "/"
Nov 25 14:59:01 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:01 | 200 |   18.716591ms |       127.0.0.1 | POST     "/api/show"
Nov 25 14:59:02 machinelearning ollama[586]: time=2024-11-25T14:59:02.002Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:59:02 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:02 | 200 |   18.164592ms |       127.0.0.1 | POST     "/api/generate"
Nov 25 14:59:03 machinelearning ollama[586]: time=2024-11-25T14:59:03.818Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:59:04 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:04 | 200 |  513.220707ms |       127.0.0.1 | POST     "/api/chat"
Nov 25 14:59:13 machinelearning ollama[586]: time=2024-11-25T14:59:13.420Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:59:13 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:13 | 200 |  480.104801ms |       127.0.0.1 | POST     "/api/chat"
Nov 25 14:59:25 machinelearning ollama[586]: time=2024-11-25T14:59:25.949Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 14:59:26 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:26 | 200 |  374.918587ms |       127.0.0.1 | POST     "/api/chat"
Nov 25 15:01:16 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:16 | 200 |       17.31µs |       127.0.0.1 | HEAD     "/"
Nov 25 15:01:16 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:16 | 200 |   18.172272ms |       127.0.0.1 | POST     "/api/show"
Nov 25 15:01:16 machinelearning ollama[586]: time=2024-11-25T15:01:16.199Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 15:01:16 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:16 | 200 |   17.658543ms |       127.0.0.1 | POST     "/api/generate"
Nov 25 15:01:17 machinelearning ollama[586]: time=2024-11-25T15:01:17.739Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 15:01:18 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:18 | 200 |  395.252708ms |       127.0.0.1 | POST     "/api/chat"
Nov 25 15:01:34 machinelearning ollama[586]: time=2024-11-25T15:01:34.190Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 15:01:40 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:40 | 200 |  6.206634214s |       127.0.0.1 | POST     "/api/chat"
Nov 25 15:02:10 machinelearning ollama[586]: time=2024-11-25T15:02:10.264Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 15:02:34 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:02:34 | 200 | 24.365532524s |       127.0.0.1 | POST     "/api/chat"
Nov 25 15:06:00 machinelearning ollama[586]: time=2024-11-25T15:06:00.997Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 15:06:09 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:06:09 | 200 |  8.635675577s |    192.168.0.15 | POST     "/api/generate"
Nov 25 15:06:09 machinelearning ollama[586]: time=2024-11-25T15:06:09.634Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet"
Nov 25 15:06:10 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:06:10 | 200 |   503.75888ms |    192.168.0.15 | POST     "/api/generate"
Nov 25 15:08:37 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:08:37 | 200 |       26.17µs |       127.0.0.1 | GET      "/api/version"
<!-- gh-comment-id:2498284490 --> @maxi1134 commented on GitHub (Nov 25, 2024): I too get "msg="mllama doesn't support parallel requests yet"". Yet I have no error 500 indicating a timeout. Could it be something else? I am on v0.4.4 ``` equests yet" Nov 25 14:53:48 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:53:48 | 200 | 2.12196848s | 192.168.0.15 | POST "/api/generate" Nov 25 14:54:16 machinelearning ollama[586]: time=2024-11-25T14:54:16.635Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:54:27 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:54:27 | 200 | 10.976419175s | 192.168.0.15 | POST "/api/generate" Nov 25 14:54:28 machinelearning ollama[586]: time=2024-11-25T14:54:28.514Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:54:29 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:54:29 | 200 | 526.881149ms | 192.168.0.15 | POST "/api/generate" Nov 25 14:55:22 machinelearning ollama[586]: time=2024-11-25T14:55:22.022Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:55:33 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:55:33 | 200 | 11.142031778s | 192.168.0.15 | POST "/api/generate" Nov 25 14:55:33 machinelearning ollama[586]: time=2024-11-25T14:55:33.167Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:55:34 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:55:34 | 200 | 1.591731104s | 192.168.0.15 | POST "/api/generate" Nov 25 14:58:26 machinelearning ollama[586]: time=2024-11-25T14:58:26.031Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:58:26 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:58:26 | 200 | 18.326325ms | ::1 | POST "/api/generate" Nov 25 14:59:01 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:01 | 200 | 39.301µs | 127.0.0.1 | HEAD "/" Nov 25 14:59:01 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:01 | 200 | 18.716591ms | 127.0.0.1 | POST "/api/show" Nov 25 14:59:02 machinelearning ollama[586]: time=2024-11-25T14:59:02.002Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:59:02 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:02 | 200 | 18.164592ms | 127.0.0.1 | POST "/api/generate" Nov 25 14:59:03 machinelearning ollama[586]: time=2024-11-25T14:59:03.818Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:59:04 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:04 | 200 | 513.220707ms | 127.0.0.1 | POST "/api/chat" Nov 25 14:59:13 machinelearning ollama[586]: time=2024-11-25T14:59:13.420Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:59:13 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:13 | 200 | 480.104801ms | 127.0.0.1 | POST "/api/chat" Nov 25 14:59:25 machinelearning ollama[586]: time=2024-11-25T14:59:25.949Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 14:59:26 machinelearning ollama[586]: [GIN] 2024/11/25 - 14:59:26 | 200 | 374.918587ms | 127.0.0.1 | POST "/api/chat" Nov 25 15:01:16 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:16 | 200 | 17.31µs | 127.0.0.1 | HEAD "/" Nov 25 15:01:16 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:16 | 200 | 18.172272ms | 127.0.0.1 | POST "/api/show" Nov 25 15:01:16 machinelearning ollama[586]: time=2024-11-25T15:01:16.199Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 15:01:16 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:16 | 200 | 17.658543ms | 127.0.0.1 | POST "/api/generate" Nov 25 15:01:17 machinelearning ollama[586]: time=2024-11-25T15:01:17.739Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 15:01:18 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:18 | 200 | 395.252708ms | 127.0.0.1 | POST "/api/chat" Nov 25 15:01:34 machinelearning ollama[586]: time=2024-11-25T15:01:34.190Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 15:01:40 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:01:40 | 200 | 6.206634214s | 127.0.0.1 | POST "/api/chat" Nov 25 15:02:10 machinelearning ollama[586]: time=2024-11-25T15:02:10.264Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 15:02:34 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:02:34 | 200 | 24.365532524s | 127.0.0.1 | POST "/api/chat" Nov 25 15:06:00 machinelearning ollama[586]: time=2024-11-25T15:06:00.997Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 15:06:09 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:06:09 | 200 | 8.635675577s | 192.168.0.15 | POST "/api/generate" Nov 25 15:06:09 machinelearning ollama[586]: time=2024-11-25T15:06:09.634Z level=WARN source=sched.go:137 msg="mllama doesn't support parallel requests yet" Nov 25 15:06:10 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:06:10 | 200 | 503.75888ms | 192.168.0.15 | POST "/api/generate" Nov 25 15:08:37 machinelearning ollama[586]: [GIN] 2024/11/25 - 15:08:37 | 200 | 26.17µs | 127.0.0.1 | GET "/api/version" ```
GiteaMirror commented 2026-04-22 10:26:55 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 25, 2024):

msg="mllama doesn't support parallel requests yet" has nothing to do with timeouts, it's just a warning saying that OLLAMA_NUM_PARALLEL is going to be treated as if it were set to 1.

<!-- gh-comment-id:2498294912 --> @rick-github commented on GitHub (Nov 25, 2024): `msg="mllama doesn't support parallel requests yet"` has nothing to do with timeouts, it's just a warning saying that `OLLAMA_NUM_PARALLEL` is going to be treated as if it were set to 1.
GiteaMirror commented 2026-04-22 10:26:55 -05:00
Author
Owner
Copy Link

@pickmao commented on GitHub (Jan 4, 2025):

same，just set env OLLAMA_NUM_PARALLEL=3，

<!-- gh-comment-id:2569994869 --> @pickmao commented on GitHub (Jan 4, 2025): same，just set env OLLAMA_NUM_PARALLEL=3，
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#30620
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?