github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11172] Long prompt causes generate API to misbehave #7368

New Issue
Open
opened 2026-04-12 19:25:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 19:25:42 -05:00
Owner
Copy Link

Originally created by @dhiltgen on GitHub (Jun 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11172

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

If you send an extremely long prompt that exceeds the context size, the generate API doesn't behave properly. If you set stream=false you never get a generate response callback. With streaming enabled, you do get a series of response callbacks, however the final response has Done==false and no timing information.

This can be seen via CLI with something like

% ollama run --verbose llama3.2:latest < ~/Documents/shakespeare.txt

which will produce some output, but never report the verbose timing information.

Relevant log output

time=2025-06-23T11:20:47.693-07:00 level=WARN source=runner.go:128 msg="truncating input prompt" limit=4096 prompt=1474469 keep=5 new=4096
time=2025-06-23T11:20:47.694-07:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=4096 used=0 remaining=4096
time=2025-06-23T11:20:50.738-07:00 level=DEBUG source=cache.go:240 msg="context limit hit - shifting" id=0 limit=4096 input=4096 keep=5 discard=2045
update: applying K-shift
time=2025-06-23T11:20:57.402-07:00 level=DEBUG source=sched.go:503 msg="context for request finished"
time=2025-06-23T11:20:57.402-07:00 level=INFO source=routes.go:1377 msg="streamResponse: w.Write failed with write tcp 127.0.0.1:11434->127.0.0.1:60644: write: connection reset by peer"
time=2025-06-23T11:20:57.402-07:00 level=DEBUG source=sched.go:343 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/llama3.2:latest runner.inference=metal runner.devices=1 runner.size="3.8 GiB" runner.vram="3.8 GiB" runner.parallel=2 runner.pid=20549 runner.model=/Users/daniel/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff runner.num_ctx=8192 duration=5m0s
[GIN] 2025/06/23 - 11:20:57 | 200 | 23.619543916s |       127.0.0.1 | POST     "/api/generate"

OS

No response

GPU

No response

CPU

No response

Ollama version

0.9.2

Originally created by @dhiltgen on GitHub (Jun 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11172 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? If you send an extremely long prompt that exceeds the context size, the generate API doesn't behave properly. If you set `stream=false` you never get a generate response callback. With streaming enabled, you do get a series of response callbacks, however the final response has Done==false and no timing information. This can be seen via CLI with something like ``` % ollama run --verbose llama3.2:latest < ~/Documents/shakespeare.txt ``` which will produce some output, but never report the verbose timing information. ### Relevant log output ```shell time=2025-06-23T11:20:47.693-07:00 level=WARN source=runner.go:128 msg="truncating input prompt" limit=4096 prompt=1474469 keep=5 new=4096 time=2025-06-23T11:20:47.694-07:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=4096 used=0 remaining=4096 time=2025-06-23T11:20:50.738-07:00 level=DEBUG source=cache.go:240 msg="context limit hit - shifting" id=0 limit=4096 input=4096 keep=5 discard=2045 update: applying K-shift time=2025-06-23T11:20:57.402-07:00 level=DEBUG source=sched.go:503 msg="context for request finished" time=2025-06-23T11:20:57.402-07:00 level=INFO source=routes.go:1377 msg="streamResponse: w.Write failed with write tcp 127.0.0.1:11434->127.0.0.1:60644: write: connection reset by peer" time=2025-06-23T11:20:57.402-07:00 level=DEBUG source=sched.go:343 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/llama3.2:latest runner.inference=metal runner.devices=1 runner.size="3.8 GiB" runner.vram="3.8 GiB" runner.parallel=2 runner.pid=20549 runner.model=/Users/daniel/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff runner.num_ctx=8192 duration=5m0s [GIN] 2025/06/23 - 11:20:57 | 200 | 23.619543916s | 127.0.0.1 | POST "/api/generate" ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.9.2
GiteaMirror added the bug label 2026-04-12 19:25:42 -05:00
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#7368
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?