mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-10 15:57:04 +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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
26 lines
1.0 KiB
Diff
26 lines
1.0 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Daniel Hiltgen <daniel@ollama.com>
|
|
Date: Sun, 3 Aug 2025 10:00:20 -0700
|
|
Subject: [PATCH] Disable ggml-blas on macos v13 and older
|
|
|
|
---
|
|
ggml/src/ggml-blas/ggml-blas.cpp | 5 +++++
|
|
1 file changed, 5 insertions(+)
|
|
|
|
diff --git a/ggml/src/ggml-blas/ggml-blas.cpp b/ggml/src/ggml-blas/ggml-blas.cpp
|
|
index 5b888cdd..2a9ff7f6 100644
|
|
--- a/ggml/src/ggml-blas/ggml-blas.cpp
|
|
+++ b/ggml/src/ggml-blas/ggml-blas.cpp
|
|
@@ -506,6 +506,11 @@ static const struct ggml_backend_reg_i ggml_backend_blas_reg_i = {
|
|
};
|
|
|
|
ggml_backend_reg_t ggml_backend_blas_reg(void) {
|
|
+ // MacOS prior to v14 does not include cblas_sgemm - disable this backend if it isn't available
|
|
+ if (&cblas_sgemm == NULL) {
|
|
+ GGML_LOG_INFO("Disabling ggml-blas backend on old MacOS version\n");
|
|
+ return NULL;
|
|
+ }
|
|
static struct ggml_backend_reg ggml_backend_blas_reg = {
|
|
/* .api_version = */ GGML_BACKEND_API_VERSION,
|
|
/* .iface = */ ggml_backend_blas_reg_i,
|