mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-10 18:06:33 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

increase default context length to 4096 (#10364)

Browse source 
* increase default context length to 4096

We lower the default numParallel from 4 to 2 and use these "savings" to
double the default context length from 2048 to 4096.

We're memory neutral in cases when we previously would've used
numParallel == 4, but we add the following mitigation to handle some
cases where we would have previously fallen back to 1x2048 due to low
VRAM: we decide between 2048 and 4096 using a runtime check, choosing
2048 if we're on a one GPU system with total VRAM of <= 4 GB. We
purposefully don't check the available VRAM because we don't want the
context window size to change unexpectedly based on the available VRAM.

We plan on making the default even larger, but this is a relatively
low-risk change we can make to quickly double it.

* fix tests

add an explicit context length so they don't get truncated. The code
that converts -1 from being a signal for doing a runtime check isn't
running as part of these tests.

* tweak small gpu message

* clarify context length default

also make it actually show up in `ollama serve --help`
This commit is contained in:
Devon Rifkin 2025-04-22 16:33:24 -07:00 • committed by GitHub
parent 2eb1fb3231
commit 424f648632
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 49 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/faq.md
View file

@ -20,7 +20,7 @@ Please refer to the [GPU docs](./gpu.md).
## How can I specify the context window size?
By default, Ollama uses a context window size of 2048 tokens.
By default, Ollama uses a context window size of 4096 tokens, unless you have a single GPU with <= 4 GB of VRAM, in which case it will default to 2048 tokens.
This can be overridden with the `OLLAMA_CONTEXT_LENGTH` environment variable. For example, to set the default context window to 8K, use:
@ -31,7 +31,7 @@ OLLAMA_CONTEXT_LENGTH=8192 ollama serve
To change this when using `ollama run`, use `/set parameter`:
```shell
/set parameter num_ctx 4096
/set parameter num_ctx 8192
```
When using the API, specify the `num_ctx` parameter:
@ -41,7 +41,7 @@ curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"options": {
"num_ctx": 4096
"num_ctx": 8192
}
}'
```