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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
35 lines
840 B
Plaintext
35 lines
840 B
Plaintext
---
|
|
title: VS Code
|
|
---
|
|
|
|
## Install
|
|
|
|
Install [VSCode](https://code.visualstudio.com/download).
|
|
|
|
## Usage with Ollama
|
|
|
|
1. Open Copilot side bar found in top right window
|
|
<div style={{ display: 'flex', justifyContent: 'center' }}>
|
|
<img
|
|
src="/images/vscode-sidebar.png"
|
|
alt="VSCode chat Sidebar"
|
|
width="75%"
|
|
/>
|
|
</div>
|
|
2. Select the model drowpdown > **Manage models**
|
|
<div style={{ display: 'flex', justifyContent: 'center' }}>
|
|
<img
|
|
src="/images/vscode-models.png"
|
|
alt="VSCode model picker"
|
|
width="75%"
|
|
/>
|
|
</div>
|
|
3. Enter **Ollama** under **Provider Dropdown** and select desired models (e.g `qwen3, qwen3-coder:480b-cloud`)
|
|
<div style={{ display: 'flex', justifyContent: 'center' }}>
|
|
<img
|
|
src="/images/vscode-model-options.png"
|
|
alt="VSCode model options dropdown"
|
|
width="75%"
|
|
/>
|
|
</div>
|