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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
39 lines
1.3 KiB
Plaintext
39 lines
1.3 KiB
Plaintext
---
|
|
title: Context length
|
|
---
|
|
|
|
Context length is the maximum number of tokens that the model has access to in memory.
|
|
|
|
<Note>
|
|
The default context length in Ollama is 4096 tokens.
|
|
</Note>
|
|
|
|
Tasks which require large context like web search, agents, and coding tools should be set to at least 32000 tokens.
|
|
|
|
## Setting context length
|
|
|
|
Setting a larger context length will increase the amount of memory required to run a model. Ensure you have enough VRAM available to increase the context length.
|
|
|
|
Cloud models are set to their maximum context length by default.
|
|
|
|
### App
|
|
|
|
Change the slider in the Ollama app under settings to your desired context length.
|
|
|
|
|
|
### CLI
|
|
If editing the context length for Ollama is not possible, the context length can also be updated when serving Ollama.
|
|
```
|
|
OLLAMA_CONTEXT_LENGTH=32000 ollama serve
|
|
```
|
|
|
|
### Check allocated context length and model offloading
|
|
For best performance, use the maximum context length for a model, and avoid offloading the model to CPU. Verify the split under `PROCESSOR` using `ollama ps`.
|
|
```
|
|
ollama ps
|
|
```
|
|
```
|
|
NAME ID SIZE PROCESSOR CONTEXT UNTIL
|
|
gemma3:latest a2af6cc3eb7f 6.6 GB 100% GPU 65536 2 minutes from now
|
|
```
|