next build (#8539)

* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install targets * remove unused files * ml: visit each library path once * build: skip cpu variants on arm * build: install cpu targets * build: fix workflow * shorter names * fix rocblas install * docs: clean up development.md * consistent build dir removal in development.md * silence -Wimplicit-function-declaration build warnings in ggml-cpu * update readme * update development readme * llm: update library lookup logic now that there is one runner (#8587) * tweak development.md * update docs * add windows cuda/rocm tests --------- Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2025-12-12 00:37:04 +00:00 · 2025-01-29 15:03:38 -08:00
parent 2ef3c803a1
commit dcfb7a105c
542 changed files with 5796 additions and 11469 deletions
--- a/llama/patches/0009-fix-deepseek-deseret-regex.patch
+++ b/llama/patches/0009-fix-deepseek-deseret-regex.patch
@@ -0,0 +1,72 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Daniel Hiltgen <daniel@ollama.com>
+Date: Fri, 25 Oct 2024 16:25:18 -0700
+Subject: [PATCH] fix deepseek deseret regex
+
+On windows compiled with gcc the c++ regex library failed to handle
+the characters
+---
+ src/llama-vocab.cpp |  2 +-
+ src/unicode.cpp     | 22 ++++++++++++++++++++++
+ 2 files changed, 23 insertions(+), 1 deletion(-)
+
+diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
+index 3fcfcaa3..8f44705a 100644
+--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
+@@ -375,7 +375,7 @@ struct llm_tokenizer_bpe : llm_tokenizer {
+             case LLAMA_VOCAB_PRE_TYPE_DEEPSEEK_LLM:
+                 regex_exprs = {
+                     "[\r\n]",
+-                    "\\s?[A-Za-zµÀ-ÖØ-öø-ƺƼ-ƿǄ-ʓʕ-ʯͰ-ͳͶͷͻ-ͽͿΆΈ-ΊΌΎ-ΡΣ-ϵϷ-ҁҊ-ԯԱ-ՖႠ-ჅᎠ-Ᏽᏸ-ᏽᲐ-ᲺᲽ-Ჿᴀ-ᴫᵫ-ᵷᵹ-ᶚḀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼℂℇℊ-ℓℕℙ-ℝℤΩℨK-ℭℯ-ℴℹℼ-ℿⅅ-ⅉⅎↃↄⰀ-ⱻⱾ-ⳤⳫ-ⳮⳲⳳꙀ-ꙭꚀ-ꚛꜢ-ꝯꝱ-ꞇꞋ-ꞎꭰ-ꮿﬀ-ﬆﬓ-ﬗＡ-Ｚａ-ｚ𐐀-𐑏𐒰-𐓓𐓘-𐓻𐲀-𐲲𐳀-𐳲𑢠-𑣟𞤀-𞥃]+",
+                    "\\s?[A-Za-zµÀ-ÖØ-öø-ƺƼ-ƿǄ-ʓʕ-ʯͰ-ͳͶͷͻ-ͽͿΆΈ-ΊΌΎ-ΡΣ-ϵϷ-ҁҊ-ԯԱ-ՖႠ-ჅᎠ-Ᏽᏸ-ᏽᲐ-ᲺᲽ-Ჿᴀ-ᴫᵫ-ᵷᵹ-ᶚḀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼιῂ-ῄῆ-ῌῐ-ΐῖ-Ίῠ-Ῥῲ-ῴῶ-ῼℂℇℊ-ℓℕℙ-ℝℤΩℨK-ℭℯ-ℴℹℼ-ℿⅅ-ⅉⅎↃↄⰀ-ⱻⱾ-ⳤⳫ-ⳮⳲⳳꙀ-ꙭꚀ-ꚛꜢ-ꝯꝱ-ꞇꞋ-ꞎꭰ-ꮿﬀ-ﬆﬓ-ﬗＡ-Ｚａ-ｚ\U00010400-\U0001044f𐒰-𐓓𐓘-𐓻𐲀-𐲲𐳀-𐳲𑢠-𑣟𞤀-𞥃]+",
+                     "\\s?[!-/:-~！-／：-～‘-‟　-。]+",
+                     "\\s+$",
+                     "[一-龥ࠀ-一가-퟿]+",
+diff --git a/src/unicode.cpp b/src/unicode.cpp
+index 7aca6544..6155da80 100644
+--- a/src/unicode.cpp
+++ b/src/unicode.cpp
+@@ -2,6 +2,11 @@
+ #define _SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING
+ #endif
+ 
+#if defined(_WIN32)
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#endif
+
+ #include "unicode.h"
+ #include "unicode-data.h"
+ 
+@@ -201,6 +206,22 @@ static std::unordered_map<std::string, uint8_t> unicode_utf8_to_byte_map() {
+ }
+ 
+ static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
+#ifdef _WIN32
+    int wlen = MultiByteToWideChar(CP_UTF8, 0, s.c_str(), -1, NULL, 0);
+    if (!wlen) {
+        throw std::invalid_argument("failed to convert regex");
+    }
+    wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
+    wlen = MultiByteToWideChar(CP_UTF8, 0, s.c_str(), -1, wbuf, wlen);
+    if (!wlen) {
+        free(wbuf);
+        throw std::invalid_argument("failed to convert regex");
+    }
+    std::wstring ret = std::wstring(wbuf);
+    free(wbuf);
+    return ret;
+#else
+
+ #if defined(__clang__)
+     // disable C++17 deprecation warning for std::codecvt_utf8
+ #    pragma clang diagnostic push
+@@ -214,6 +235,7 @@ static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
+ #endif
+ 
+     return conv.from_bytes(s);
+#endif
+ }
+ 
+ static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) {