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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
34 lines
1.1 KiB
Diff
34 lines
1.1 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: jmorganca <jmorganca@gmail.com>
|
|
Date: Tue, 8 Apr 2025 20:36:41 -0700
|
|
Subject: [PATCH] ollama debug tensor
|
|
|
|
---
|
|
ggml/src/ggml-cpu/ggml-cpu.c | 6 ++++++
|
|
1 file changed, 6 insertions(+)
|
|
|
|
diff --git a/ggml/src/ggml-cpu/ggml-cpu.c b/ggml/src/ggml-cpu/ggml-cpu.c
|
|
index ba2a36d9..99509b0c 100644
|
|
--- a/ggml/src/ggml-cpu/ggml-cpu.c
|
|
+++ b/ggml/src/ggml-cpu/ggml-cpu.c
|
|
@@ -15,6 +15,8 @@
|
|
#include "ops.h"
|
|
#include "ggml.h"
|
|
|
|
+#include "ollama-debug.h"
|
|
+
|
|
#if defined(_MSC_VER) || defined(__MINGW32__)
|
|
#include <malloc.h> // using malloc.h with MSC/MINGW
|
|
#elif !defined(__FreeBSD__) && !defined(__NetBSD__) && !defined(__OpenBSD__)
|
|
@@ -2887,6 +2889,10 @@ static thread_ret_t ggml_graph_compute_thread(void * data) {
|
|
|
|
ggml_compute_forward(¶ms, node);
|
|
|
|
+#ifdef OLLAMA_DEBUG
|
|
+ ollama_debug(node, true);
|
|
+#endif
|
|
+
|
|
if (state->ith == 0 && cplan->abort_callback &&
|
|
cplan->abort_callback(cplan->abort_callback_data)) {
|
|
atomic_store_explicit(&tp->abort, node_n + 1, memory_order_relaxed);
|