mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-18 11:47:07 +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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
57 lines
1.0 KiB
Plaintext
57 lines
1.0 KiB
Plaintext
---
|
|
title: Codex
|
|
---
|
|
|
|
|
|
## Install
|
|
|
|
Install the [Codex CLI](https://developers.openai.com/codex/cli/):
|
|
|
|
```
|
|
npm install -g @openai/codex
|
|
```
|
|
|
|
## Usage with Ollama
|
|
|
|
<Note>Codex requires a larger context window. It is recommended to use a context window of at least 32K tokens.</Note>
|
|
|
|
To use `codex` with Ollama, use the `--oss` flag:
|
|
|
|
```
|
|
codex --oss
|
|
```
|
|
|
|
### Changing Models
|
|
|
|
By default, codex will use the local `gpt-oss:20b` model. However, you can specify a different model with the `-m` flag:
|
|
|
|
```
|
|
codex --oss -m gpt-oss:120b
|
|
```
|
|
|
|
### Cloud Models
|
|
|
|
```
|
|
codex --oss -m gpt-oss:120b-cloud
|
|
```
|
|
|
|
|
|
## Connecting to ollama.com
|
|
|
|
|
|
Create an [API key](https://ollama.com/settings/keys) from ollama.com and export it as `OLLAMA_API_KEY`.
|
|
|
|
To use ollama.com directly, edit your `~/.codex/config.toml` file to point to ollama.com.
|
|
|
|
```toml
|
|
model = "gpt-oss:120b"
|
|
model_provider = "ollama"
|
|
|
|
[model_providers.ollama]
|
|
name = "Ollama"
|
|
base_url = "https://ollama.com/v1"
|
|
env_key = "OLLAMA_API_KEY"
|
|
```
|
|
|
|
Run `codex` in a new terminal to load the new settings.
|