github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13285] Ollama's responses have about 4 sec pause between chunks of token sent #8780

New Issue
Closed
opened 2026-04-12 21:32:45 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 21:32:45 -05:00
Owner
Copy Link

Originally created by @nithin-bg on GitHub (Dec 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13285

I am using a dot net application to receive tokens from Ollama.

API Request:
EndPoint: "http://localhost:11434/api/generate" - POST
Payload:
{
"model": "llama3.1:8b",
"prompt": "Explain French Revolution in detail",
"stream": true,
}
When I trigger this API request, In long responses I am getting about 4 seconds delay after receiving some chunks (about 100 - 150 tokens) of token and then after some chunks again about 4 seconds of delay... and so on.

Is this how Ollama gives response or any other reason?

Sample Code:

public async IAsyncEnumerable<string> ChatStream(StringContent requestContent, CancellationToken cancellationToken)
{
    var request = new HttpRequestMessage(HttpMethod.Post, _apiEndpoint)
    { Content = requestContent };
    using var response = await _httpClient.SendAsync(request, HttpCompletionOption.ResponseHeadersRead, cancellationToken);
    response.EnsureSuccessStatusCode();
    await using var responseStream = await response.Content.ReadAsStreamAsync(cancellationToken);
    using var reader = new StreamReader(responseStream);
    string token = null;
    while (!reader.EndOfStream)
    {
        var line = await reader.ReadLineAsync(cancellationToken);
        if (string.IsNullOrWhiteSpace(line))
            continue;
        if (!string.IsNullOrEmpty(line))
        {
            Console.WriteLine($"Token received at {DateTime.Now:yyyy-MM-dd HH:mm:ss.ffffffzzz}");
            yield return line;
        }
    }
}
Originally created by @nithin-bg on GitHub (Dec 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13285 I am using a dot net application to receive tokens from Ollama. API Request: EndPoint: "http://localhost:11434/api/generate" - POST Payload: { "model": "llama3.1:8b", "prompt": "Explain French Revolution in detail", "stream": true, } When I trigger this API request, In long responses I am getting about 4 seconds delay after receiving some chunks (about 100 - 150 tokens) of token and then after some chunks again about 4 seconds of delay... and so on. **Is this how Ollama gives response or any other reason?** Sample Code: ``` public async IAsyncEnumerable<string> ChatStream(StringContent requestContent, CancellationToken cancellationToken) { var request = new HttpRequestMessage(HttpMethod.Post, _apiEndpoint) { Content = requestContent }; using var response = await _httpClient.SendAsync(request, HttpCompletionOption.ResponseHeadersRead, cancellationToken); response.EnsureSuccessStatusCode(); await using var responseStream = await response.Content.ReadAsStreamAsync(cancellationToken); using var reader = new StreamReader(responseStream); string token = null; while (!reader.EndOfStream) { var line = await reader.ReadLineAsync(cancellationToken); if (string.IsNullOrWhiteSpace(line)) continue; if (!string.IsNullOrEmpty(line)) { Console.WriteLine($"Token received at {DateTime.Now:yyyy-MM-dd HH:mm:ss.ffffffzzz}"); yield return line; } } } ```
GiteaMirror commented 2026-04-12 21:32:46 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 1, 2025):

Does the same thing happen if you use the API directly?

curl http://localhost:11434/api/generate -d "{\"model\":\"llama3.1:8b\",\"prompt\":\"Explain French Revolution in detail\",\"stream\":true}"

What OS?
What GPU?
What CPU?
What version of ollama?

<!-- gh-comment-id:3597593615 --> @rick-github commented on GitHub (Dec 1, 2025): Does the same thing happen if you use the API directly? ``` curl http://localhost:11434/api/generate -d "{\"model\":\"llama3.1:8b\",\"prompt\":\"Explain French Revolution in detail\",\"stream\":true}" ``` What OS? What GPU? What CPU? What version of ollama?
GiteaMirror commented 2026-04-12 21:32:47 -05:00
Author
Owner
Copy Link

@nithin-bg commented on GitHub (Dec 2, 2025):

I'm not facing this issue in curl.

OS: Ubuntu 24.04.3 LTS
GPU: NVIDIA H100 NVL:- 96GB
CPU: 314 GB
ollama: 0.12.0

<!-- gh-comment-id:3600245293 --> @nithin-bg commented on GitHub (Dec 2, 2025): I'm not facing this issue in curl. OS: Ubuntu 24.04.3 LTS GPU: NVIDIA H100 NVL:- 96GB CPU: 314 GB ollama: 0.12.0
GiteaMirror commented 2026-04-12 21:32:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 2, 2025):

Seems like an app issue. Is your reader buffering input? What happens if you don't use async calls?

<!-- gh-comment-id:3601362818 --> @rick-github commented on GitHub (Dec 2, 2025): Seems like an app issue. Is your reader buffering input? What happens if you don't use async calls?
GiteaMirror commented 2026-04-12 21:32:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 3, 2025):

Resolved by upgrading HTTPClient version from 1.1 to 2.0.

<!-- gh-comment-id:3609072521 --> @rick-github commented on GitHub (Dec 3, 2025): Resolved by [upgrading](https://discord.com/channels/1128867683291627614/1444736133039652965/1445622534015025253) HTTPClient version from 1.1 to 2.0.
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
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#8780
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?