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 #12087] Ollama Turbo Deepseek non-stream with options results in upstream error 502 #8030

New Issue
Closed
opened 2026-04-12 20:16:18 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 20:16:18 -05:00
Owner
Copy Link

Originally created by @MarkWard0110 on GitHub (Aug 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12087

Originally assigned to: @jmorganca on GitHub.

What is the issue?

Ollama Turbo, when using deepseek-v3.1:671b non-stream chat request with options set, will result in a upstream error 502 response.

Was able to replicate using ollama-python gpt-oss-tools.py example with the model set to deepseek-v3.1:671b

snippit

model = 'deepseek-v3.1:671b'

while True:
  response: ChatResponse = client.chat(model=model, messages=messages, tools=[get_weather, get_weather_conditions],options={
                "temperature": 0,
                "top_p": 0,
                "top_k": 1,
                "num_ctx": 64000,
                "num_predict": 8196
            })

When run it will error with an upstream error 502 response.

Relevant log output

OS

Windows 11

GPU

Ollama Turbo

CPU

Ollama Turbo

Ollama version

Ollama Turbo

Originally created by @MarkWard0110 on GitHub (Aug 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12087 Originally assigned to: @jmorganca on GitHub. ### What is the issue? Ollama Turbo, when using `deepseek-v3.1:671b` non-stream chat request with `options` set, will result in a `upstream error 502` response. Was able to replicate using `ollama-python` `gpt-oss-tools.py` example with the model set to `deepseek-v3.1:671b` snippit ``` model = 'deepseek-v3.1:671b' while True: response: ChatResponse = client.chat(model=model, messages=messages, tools=[get_weather, get_weather_conditions],options={ "temperature": 0, "top_p": 0, "top_k": 1, "num_ctx": 64000, "num_predict": 8196 }) ``` When run it will error with an `upstream error 502` response. ### Relevant log output ```shell ``` ### OS Windows 11 ### GPU Ollama Turbo ### CPU Ollama Turbo ### Ollama version Ollama Turbo
GiteaMirror added the bug label 2026-04-12 20:16:18 -05:00
GiteaMirror commented 2026-04-12 20:16:20 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Aug 26, 2025):

This should be fixed now. Thanks for reporting!

<!-- gh-comment-id:3224984203 --> @jmorganca commented on GitHub (Aug 26, 2025): This should be fixed now. Thanks for reporting!
GiteaMirror commented 2026-04-12 20:16:21 -05:00
Author
Owner
Copy Link

@MarkWard0110 commented on GitHub (Aug 28, 2025):

@jmorganca I think it is working! Thank you!

<!-- gh-comment-id:3233758383 --> @MarkWard0110 commented on GitHub (Aug 28, 2025): @jmorganca I think it is working! Thank you!
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#8030
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?