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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
1.5 KiB
Integration Tests
This directory contains integration tests to exercise Ollama end-to-end to verify behavior
By default, these tests are disabled so go test ./... will exercise only unit tests. To run integration tests you must pass the integration tag. go test -tags=integration ./... Some tests require additional tags to enable to allow scoped testing to keep the duration reasonable. For example, testing a broad set of models requires -tags=integration,models and a longer timeout (~60m or more depending on the speed of your GPU.). To view the current set of tag combinations use find integration -type f | xargs grep "go:build"
The integration tests have 2 modes of operating.
- By default, on Unix systems, they will start the server on a random port, run the tests, and then shutdown the server. On Windows you must ALWAYS run the server on OLLAMA_HOST for the tests to work.
- If
OLLAMA_TEST_EXISTINGis set to a non-empty string, the tests will run against an existing running server, which can be remote based on yourOLLAMA_HOSTenvironment variable
Important
Before running the tests locally without the "test existing" setting, compile ollama from the top of the source tree
go build .in addition to GPU support with cmake if applicable on your platform. The integration tests expect to find an ollama binary at the top of the tree.
Many tests use a default small model suitable to run on many systems. You can override this default model by setting OLLAMA_TEST_DEFAULT_MODEL