mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-09 23:37:06 +00:00
ef14fb5b26
This commit represents a complete rework after pulling the latest changes from official ollama/ollama repository and re-applying Tesla K80 compatibility patches. ## Key Changes ### CUDA Compute Capability 3.7 Support (Tesla K80) - Added sm_37 (compute 3.7) to CMAKE_CUDA_ARCHITECTURES in CMakeLists.txt - Updated CMakePresets.json to include compute 3.7 in "CUDA 11" preset - Using 37-virtual (PTX with JIT compilation) for maximum compatibility ### Legacy Toolchain Compatibility - **NVIDIA Driver**: 470.256.02 (last version supporting Kepler/K80) - **CUDA Version**: 11.4.4 (last CUDA 11.x supporting compute 3.7) - **GCC Version**: 10.5.0 (required by CUDA 11.4 host_config.h) ### CPU Architecture Trade-offs Due to GCC 10.5 limitation, sacrificed newer CPU optimizations: - Alderlake CPU variant enabled WITHOUT AVX_VNNI (requires GCC 11+) - Still supports: SSE4.2, AVX, F16C, AVX2, BMI2, FMA - Performance impact: ~3-7% on newer CPUs (acceptable for K80 compatibility) ### Build System Updates - Modified ml/backend/ggml/ggml/src/ggml-cuda/CMakeLists.txt for compute 3.7 - Added -Wno-deprecated-gpu-targets flag to suppress warnings - Updated ml/backend/ggml/ggml/src/CMakeLists.txt for Alderlake without AVX_VNNI ### Upstream Sync Merged latest llama.cpp changes including: - Enhanced KV cache management with ISWA and hybrid memory support - Improved multi-modal support (mtmd framework) - New model architectures (Gemma3, Llama4, Qwen3, etc.) - GPU backend improvements for CUDA, Metal, and ROCm - Updated quantization support and GGUF format handling ### Documentation - Updated CLAUDE.md with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was dropped in official Ollama due to legacy driver/CUDA requirements. The toolchain constraint creates a deadlock: - K80 → Driver 470 → CUDA 11.4 → GCC 10 → No AVX_VNNI We accept the loss of cutting-edge CPU optimizations to enable running modern LLMs on legacy but still capable Tesla K80 hardware (12GB VRAM per GPU). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
104 lines
1.9 KiB
Plaintext
104 lines
1.9 KiB
Plaintext
---
|
|
title: Quickstart
|
|
---
|
|
|
|
This quickstart will walk your through running your first model with Ollama. To get started, download Ollama on macOS, Windows or Linux.
|
|
|
|
<a
|
|
href="https://ollama.com/download"
|
|
target="_blank"
|
|
className="inline-block px-6 py-2 bg-black rounded-full dark:bg-neutral-700 text-white font-normal border-none"
|
|
>
|
|
Download Ollama
|
|
</a>
|
|
|
|
## Run a model
|
|
|
|
<Tabs>
|
|
<Tab title="CLI">
|
|
Open a terminal and run the command:
|
|
|
|
```
|
|
ollama run gemma3
|
|
```
|
|
|
|
</Tab>
|
|
<Tab title="cURL">
|
|
```
|
|
ollama pull gemma3
|
|
```
|
|
|
|
Lastly, chat with the model:
|
|
|
|
```shell
|
|
curl http://localhost:11434/api/chat -d '{
|
|
"model": "gemma3",
|
|
"messages": [{
|
|
"role": "user",
|
|
"content": "Hello there!"
|
|
}],
|
|
"stream": false
|
|
}'
|
|
```
|
|
|
|
</Tab>
|
|
<Tab title="Python">
|
|
Start by downloading a model:
|
|
|
|
```
|
|
ollama pull gemma3
|
|
```
|
|
|
|
Then install Ollama's Python library:
|
|
|
|
```
|
|
pip install ollama
|
|
```
|
|
|
|
Lastly, chat with the model:
|
|
|
|
```python
|
|
from ollama import chat
|
|
from ollama import ChatResponse
|
|
|
|
response: ChatResponse = chat(model='gemma3', messages=[
|
|
{
|
|
'role': 'user',
|
|
'content': 'Why is the sky blue?',
|
|
},
|
|
])
|
|
print(response['message']['content'])
|
|
# or access fields directly from the response object
|
|
print(response.message.content)
|
|
```
|
|
|
|
</Tab>
|
|
<Tab title="JavaScript">
|
|
Start by downloading a model:
|
|
|
|
```
|
|
ollama pull gemma3
|
|
```
|
|
|
|
Then install the Ollama JavaScript library:
|
|
```
|
|
npm i ollama
|
|
```
|
|
|
|
Lastly, chat with the model:
|
|
|
|
```shell
|
|
import ollama from 'ollama'
|
|
|
|
const response = await ollama.chat({
|
|
model: 'gemma3',
|
|
messages: [{ role: 'user', content: 'Why is the sky blue?' }],
|
|
})
|
|
console.log(response.message.content)
|
|
```
|
|
|
|
</Tab>
|
|
</Tabs>
|
|
|
|
See a full list of available models [here](https://ollama.com/models).
|