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 #4623] The ollama server is stopped when I submitted jobs parallelly #2904

New Issue
Closed
opened 2026-04-12 13:15:32 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 13:15:32 -05:00
Owner
Copy Link

Originally created by @inoue0426 on GitHub (May 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4623

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Hi,

When I submitted below, suddenly the server just shows POST and doesn't show HEAD and stop.
Do you know how to deal with this?

Python interface.

def run_test(t):
    subprocess.run(['./summary.sh', str(t)])
    
Parallel(n_jobs=-1)(delayed(run_test)(t) for t in tqdm(untested))

shell script

(torch) ➜  review git:(main) ✗ cat summary.sh 
#!/bin/zsh

output=$(./ollama-darwin run llama3:8b-instruct-q5_K_M \
  "Summarise below prompt. No explanation, just return summarized text. \
  INPUT TEXT: "${1}" ")

processed_output=$(echo "${output}" | tr -d ',' | tr '"' ',' | tr -d "'" | tr -d '\n')

echo "\"${1}\",\"${processed_output}\"" >> summary.csv%                                             (torch) ➜  review git:(main) ✗

ollama server log

[GIN] 2024/05/24 - 17:09:06 | 200 |      20.916µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/05/24 - 17:09:06 | 200 |         363µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/05/24 - 17:09:06 | 200 | 11.275035333s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:07 | 200 |      18.917µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/05/24 - 17:09:07 | 200 |     394.625µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/05/24 - 17:09:07 | 200 | 10.529125125s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:07 | 200 |      20.333µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/05/24 - 17:09:07 | 200 |       441.5µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/05/24 - 17:09:08 | 200 |   10.6834455s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:08 | 200 |      21.125µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/05/24 - 17:09:08 | 200 |     833.125µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/05/24 - 17:09:09 | 200 | 10.325507834s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:11 | 200 | 10.764251375s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:12 | 200 | 10.599380292s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:14 | 200 | 10.261547416s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:15 | 200 |  9.766182917s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:16 | 200 | 10.306288125s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:17 | 200 | 10.834983416s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:19 | 200 |  12.06265875s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:20 | 200 | 12.753880667s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:20 | 200 | 12.012651375s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/05/24 - 17:09:54 | 200 |        18.5µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/05/24 - 17:09:54 | 200 |    2.248125ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/05/24 - 17:09:55 | 200 |  1.189454292s |       127.0.0.1 | POST     "/api/generate"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.38

Originally created by @inoue0426 on GitHub (May 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4623 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Hi, When I submitted below, suddenly the server just shows POST and doesn't show HEAD and stop. Do you know how to deal with this? ## Python interface. ```python def run_test(t): subprocess.run(['./summary.sh', str(t)]) Parallel(n_jobs=-1)(delayed(run_test)(t) for t in tqdm(untested)) ``` ## shell script ```sh (torch) ➜ review git:(main) ✗ cat summary.sh #!/bin/zsh output=$(./ollama-darwin run llama3:8b-instruct-q5_K_M \ "Summarise below prompt. No explanation, just return summarized text. \ INPUT TEXT: "${1}" ") processed_output=$(echo "${output}" | tr -d ',' | tr '"' ',' | tr -d "'" | tr -d '\n') echo "\"${1}\",\"${processed_output}\"" >> summary.csv% (torch) ➜ review git:(main) ✗ ``` ## ollama server log ``` [GIN] 2024/05/24 - 17:09:06 | 200 | 20.916µs | 127.0.0.1 | HEAD "/" [GIN] 2024/05/24 - 17:09:06 | 200 | 363µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/05/24 - 17:09:06 | 200 | 11.275035333s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:07 | 200 | 18.917µs | 127.0.0.1 | HEAD "/" [GIN] 2024/05/24 - 17:09:07 | 200 | 394.625µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/05/24 - 17:09:07 | 200 | 10.529125125s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:07 | 200 | 20.333µs | 127.0.0.1 | HEAD "/" [GIN] 2024/05/24 - 17:09:07 | 200 | 441.5µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/05/24 - 17:09:08 | 200 | 10.6834455s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:08 | 200 | 21.125µs | 127.0.0.1 | HEAD "/" [GIN] 2024/05/24 - 17:09:08 | 200 | 833.125µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/05/24 - 17:09:09 | 200 | 10.325507834s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:11 | 200 | 10.764251375s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:12 | 200 | 10.599380292s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:14 | 200 | 10.261547416s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:15 | 200 | 9.766182917s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:16 | 200 | 10.306288125s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:17 | 200 | 10.834983416s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:19 | 200 | 12.06265875s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:20 | 200 | 12.753880667s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:20 | 200 | 12.012651375s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/05/24 - 17:09:54 | 200 | 18.5µs | 127.0.0.1 | HEAD "/" [GIN] 2024/05/24 - 17:09:54 | 200 | 2.248125ms | 127.0.0.1 | POST "/api/show" [GIN] 2024/05/24 - 17:09:55 | 200 | 1.189454292s | 127.0.0.1 | POST "/api/generate" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.38
GiteaMirror added the needs more info label 2026-04-12 13:15:32 -05:00
GiteaMirror commented 2026-04-12 13:15:34 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 25, 2024):

Can you elaborate? When you say "ollama server is stopped" do you mean it crashed? If so, the server logs you included don't seem to show this.

Please upgrade to the latest version which now has concurrency enabled by default, so it should have better behavior for parallel requests. Hopefully that resolves your problem, but if not, please explain a bit more about how it is failing.

<!-- gh-comment-id:2251577899 --> @dhiltgen commented on GitHub (Jul 25, 2024): Can you elaborate? When you say "ollama server is stopped" do you mean it crashed? If so, the server logs you included don't seem to show this. Please upgrade to the latest version which now has concurrency enabled by default, so it should have better behavior for parallel requests. Hopefully that resolves your problem, but if not, please explain a bit more about how it is failing.
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 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#2904
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?