mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-10 07:46:59 +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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
69 lines
1.6 KiB
YAML
69 lines
1.6 KiB
YAML
name: Bug report
|
|
labels: [bug]
|
|
description: Something isn't working right.
|
|
body:
|
|
- type: textarea
|
|
id: description
|
|
attributes:
|
|
label: What is the issue?
|
|
description: What happened? What did you expect to happen?
|
|
validations:
|
|
required: true
|
|
- type: textarea
|
|
id: logs
|
|
attributes:
|
|
label: Relevant log output
|
|
description: Please copy and paste any relevant log output. See [Troubleshooting Guide](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) for details.
|
|
render: shell
|
|
validations:
|
|
required: false
|
|
- type: dropdown
|
|
id: os
|
|
attributes:
|
|
label: OS
|
|
description: Which operating system are you using?
|
|
multiple: true
|
|
options:
|
|
- Linux
|
|
- macOS
|
|
- Windows
|
|
- Docker
|
|
- WSL2
|
|
validations:
|
|
required: false
|
|
- type: dropdown
|
|
id: gpu
|
|
attributes:
|
|
label: GPU
|
|
description: Which GPU are you using?
|
|
multiple: true
|
|
options:
|
|
- Nvidia
|
|
- AMD
|
|
- Intel
|
|
- Apple
|
|
- Other
|
|
validations:
|
|
required: false
|
|
- type: dropdown
|
|
id: cpu
|
|
attributes:
|
|
label: CPU
|
|
description: Which CPU are you using?
|
|
multiple: true
|
|
options:
|
|
- Intel
|
|
- AMD
|
|
- Apple
|
|
- Other
|
|
validations:
|
|
required: false
|
|
- type: input
|
|
id: version
|
|
attributes:
|
|
label: Ollama version
|
|
description: What version of Ollama are you using? (`ollama --version`)
|
|
placeholder: e.g., 0.1.32
|
|
validations:
|
|
required: false
|