mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-18 11:47:07 +00:00
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with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was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>
188 lines
6.5 KiB
C++
Vendored
188 lines
6.5 KiB
C++
Vendored
// __ _____ _____ _____
|
|
// __| | __| | | | JSON for Modern C++
|
|
// | | |__ | | | | | | version 3.12.0
|
|
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
|
|
//
|
|
// SPDX-FileCopyrightText: 2013 - 2025 Niels Lohmann <https://nlohmann.me>
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#ifndef INCLUDE_NLOHMANN_JSON_FWD_HPP_
|
|
#define INCLUDE_NLOHMANN_JSON_FWD_HPP_
|
|
|
|
#include <cstdint> // int64_t, uint64_t
|
|
#include <map> // map
|
|
#include <memory> // allocator
|
|
#include <string> // string
|
|
#include <vector> // vector
|
|
|
|
// #include <nlohmann/detail/abi_macros.hpp>
|
|
// __ _____ _____ _____
|
|
// __| | __| | | | JSON for Modern C++
|
|
// | | |__ | | | | | | version 3.12.0
|
|
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
|
|
//
|
|
// SPDX-FileCopyrightText: 2013 - 2025 Niels Lohmann <https://nlohmann.me>
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
|
|
|
|
// This file contains all macro definitions affecting or depending on the ABI
|
|
|
|
#ifndef JSON_SKIP_LIBRARY_VERSION_CHECK
|
|
#if defined(NLOHMANN_JSON_VERSION_MAJOR) && defined(NLOHMANN_JSON_VERSION_MINOR) && defined(NLOHMANN_JSON_VERSION_PATCH)
|
|
#if NLOHMANN_JSON_VERSION_MAJOR != 3 || NLOHMANN_JSON_VERSION_MINOR != 12 || NLOHMANN_JSON_VERSION_PATCH != 0
|
|
#warning "Already included a different version of the library!"
|
|
#endif
|
|
#endif
|
|
#endif
|
|
|
|
#define NLOHMANN_JSON_VERSION_MAJOR 3 // NOLINT(modernize-macro-to-enum)
|
|
#define NLOHMANN_JSON_VERSION_MINOR 12 // NOLINT(modernize-macro-to-enum)
|
|
#define NLOHMANN_JSON_VERSION_PATCH 0 // NOLINT(modernize-macro-to-enum)
|
|
|
|
#ifndef JSON_DIAGNOSTICS
|
|
#define JSON_DIAGNOSTICS 0
|
|
#endif
|
|
|
|
#ifndef JSON_DIAGNOSTIC_POSITIONS
|
|
#define JSON_DIAGNOSTIC_POSITIONS 0
|
|
#endif
|
|
|
|
#ifndef JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
|
|
#define JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON 0
|
|
#endif
|
|
|
|
#if JSON_DIAGNOSTICS
|
|
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS _diag
|
|
#else
|
|
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS
|
|
#endif
|
|
|
|
#if JSON_DIAGNOSTIC_POSITIONS
|
|
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTIC_POSITIONS _dp
|
|
#else
|
|
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTIC_POSITIONS
|
|
#endif
|
|
|
|
#if JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON
|
|
#define NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON _ldvcmp
|
|
#else
|
|
#define NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON
|
|
#endif
|
|
|
|
#ifndef NLOHMANN_JSON_NAMESPACE_NO_VERSION
|
|
#define NLOHMANN_JSON_NAMESPACE_NO_VERSION 0
|
|
#endif
|
|
|
|
// Construct the namespace ABI tags component
|
|
#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c) json_abi ## a ## b ## c
|
|
#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c) \
|
|
NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c)
|
|
|
|
#define NLOHMANN_JSON_ABI_TAGS \
|
|
NLOHMANN_JSON_ABI_TAGS_CONCAT( \
|
|
NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS, \
|
|
NLOHMANN_JSON_ABI_TAG_LEGACY_DISCARDED_VALUE_COMPARISON, \
|
|
NLOHMANN_JSON_ABI_TAG_DIAGNOSTIC_POSITIONS)
|
|
|
|
// Construct the namespace version component
|
|
#define NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT_EX(major, minor, patch) \
|
|
_v ## major ## _ ## minor ## _ ## patch
|
|
#define NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT(major, minor, patch) \
|
|
NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT_EX(major, minor, patch)
|
|
|
|
#if NLOHMANN_JSON_NAMESPACE_NO_VERSION
|
|
#define NLOHMANN_JSON_NAMESPACE_VERSION
|
|
#else
|
|
#define NLOHMANN_JSON_NAMESPACE_VERSION \
|
|
NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT(NLOHMANN_JSON_VERSION_MAJOR, \
|
|
NLOHMANN_JSON_VERSION_MINOR, \
|
|
NLOHMANN_JSON_VERSION_PATCH)
|
|
#endif
|
|
|
|
// Combine namespace components
|
|
#define NLOHMANN_JSON_NAMESPACE_CONCAT_EX(a, b) a ## b
|
|
#define NLOHMANN_JSON_NAMESPACE_CONCAT(a, b) \
|
|
NLOHMANN_JSON_NAMESPACE_CONCAT_EX(a, b)
|
|
|
|
#ifndef NLOHMANN_JSON_NAMESPACE
|
|
#define NLOHMANN_JSON_NAMESPACE \
|
|
nlohmann::NLOHMANN_JSON_NAMESPACE_CONCAT( \
|
|
NLOHMANN_JSON_ABI_TAGS, \
|
|
NLOHMANN_JSON_NAMESPACE_VERSION)
|
|
#endif
|
|
|
|
#ifndef NLOHMANN_JSON_NAMESPACE_BEGIN
|
|
#define NLOHMANN_JSON_NAMESPACE_BEGIN \
|
|
namespace nlohmann \
|
|
{ \
|
|
inline namespace NLOHMANN_JSON_NAMESPACE_CONCAT( \
|
|
NLOHMANN_JSON_ABI_TAGS, \
|
|
NLOHMANN_JSON_NAMESPACE_VERSION) \
|
|
{
|
|
#endif
|
|
|
|
#ifndef NLOHMANN_JSON_NAMESPACE_END
|
|
#define NLOHMANN_JSON_NAMESPACE_END \
|
|
} /* namespace (inline namespace) NOLINT(readability/namespace) */ \
|
|
} // namespace nlohmann
|
|
#endif
|
|
|
|
|
|
/*!
|
|
@brief namespace for Niels Lohmann
|
|
@see https://github.com/nlohmann
|
|
@since version 1.0.0
|
|
*/
|
|
NLOHMANN_JSON_NAMESPACE_BEGIN
|
|
|
|
/*!
|
|
@brief default JSONSerializer template argument
|
|
|
|
This serializer ignores the template arguments and uses ADL
|
|
([argument-dependent lookup](https://en.cppreference.com/w/cpp/language/adl))
|
|
for serialization.
|
|
*/
|
|
template<typename T = void, typename SFINAE = void>
|
|
struct adl_serializer;
|
|
|
|
/// a class to store JSON values
|
|
/// @sa https://json.nlohmann.me/api/basic_json/
|
|
template<template<typename U, typename V, typename... Args> class ObjectType =
|
|
std::map,
|
|
template<typename U, typename... Args> class ArrayType = std::vector,
|
|
class StringType = std::string, class BooleanType = bool,
|
|
class NumberIntegerType = std::int64_t,
|
|
class NumberUnsignedType = std::uint64_t,
|
|
class NumberFloatType = double,
|
|
template<typename U> class AllocatorType = std::allocator,
|
|
template<typename T, typename SFINAE = void> class JSONSerializer =
|
|
adl_serializer,
|
|
class BinaryType = std::vector<std::uint8_t>, // cppcheck-suppress syntaxError
|
|
class CustomBaseClass = void>
|
|
class basic_json;
|
|
|
|
/// @brief JSON Pointer defines a string syntax for identifying a specific value within a JSON document
|
|
/// @sa https://json.nlohmann.me/api/json_pointer/
|
|
template<typename RefStringType>
|
|
class json_pointer;
|
|
|
|
/*!
|
|
@brief default specialization
|
|
@sa https://json.nlohmann.me/api/json/
|
|
*/
|
|
using json = basic_json<>;
|
|
|
|
/// @brief a minimal map-like container that preserves insertion order
|
|
/// @sa https://json.nlohmann.me/api/ordered_map/
|
|
template<class Key, class T, class IgnoredLess, class Allocator>
|
|
struct ordered_map;
|
|
|
|
/// @brief specialization that maintains the insertion order of object keys
|
|
/// @sa https://json.nlohmann.me/api/ordered_json/
|
|
using ordered_json = basic_json<nlohmann::ordered_map>;
|
|
|
|
NLOHMANN_JSON_NAMESPACE_END
|
|
|
|
#endif // INCLUDE_NLOHMANN_JSON_FWD_HPP_
|