mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-22 23:03:55 +00:00
update vendored llama.cpp and ggml (#11823)
* TEMPORARY: Update the llama.cpp upstream to my fork's Granite Four branch
This will be redone once my branch is merged upstream in llama.cpp
* feat: Update all patches
There are a number that are no longer needed at all:
- 0003-embeddings: Embeddings entirely overhauled on master
- 0008-ensure-KV-cache-is-fully-defragmented: KV caching entirely
overhauled on master
- 0019-metal-add-mean-kernel-14267: Merged upstream
- 0020-CUDA-add-mean-operation-14313: Merged upstream
* feat: Sync llama.cpp and ggml
* fix: Update rsync-filter for all moved/new/removed files
* fix: Add files missing from sync
* fix: Update ggml rsync-filter for new ggml-cpu/arch subdirs
* fix: Add ggml files missing from sync
* fix: Narrow llama.cpp rsync-filter to not include mtmd main tool cpp files
* fix: Remove mtmd main cpp files
* fix: Add missing include in sampling_ext.cpp
* fix: Update llama.go to use mtmd instead of clip/llava
* fix: Add patch for mtmd_input_text
* chore: Ignore *.patched in the patch directory
* fix: Fix support for arch-specific ggml-cpu source files with new arrangement
In https://github.com/ggml-org/llama.cpp/pull/13892, all arch-specific
implementations were split out into a nested tree structure under
ggml-cpu/arch. This conflicts with standard CGO layout where all
arch-specific source files are expected to live in the same directory as
the parent go module and use suffixes based on GOOS and GOARCH. As such,
there were really two options for getting this to work:
1. Add a patch on top of the GGML sync to rearrange the files to match the
GO layout convention
2. Use CGO directives to conditionally include the nested source files in
the compilation units
This commit does (2) in order to minimize the set of changes needed on top
of the upstream file layout. To get this to work, there are two key things
needed:
1. In cpu.go, #cgo directives are added to explicitly set __${GOARCH}__ in
the preprocessor directives
2. In arch-impls.c|cpp, use an #ifdef | #elif defined | #endif chain to
explicitly include the .c|.cpp files for the given architecture from the
nested directory
* fix: Use mtmd_helper to correctly load the bitmap for the image
* fix: Apply patch for mtmd_text_input
* fix: Add missing stb to llama.cpp rsync-filter
* fix: Add sync'ed stb vendored header
* fix: Use c++17 and include vendor for go wrapper modules
* fix: Update patch 0015 for upstream implementation of uuid
* feat: Bump to the latest tip of the branch
* fix: Update patches for bump
* feat: Bump back to the cenral repo and point at the latest master
This includes granite 4 and a number of other model architectures!
* fix: Revert changes to ggml export GPU UUID patch
* fix: Add patch for GGML_VERSION and GGML_COMMIT constants
* feat: Sync all patched code
* build: Include cmake/common.cmake in ggml sync
* build: Add top-level include for GNUINstallDirs in CMakeLists.txt
This is used to populate CMAKE_INSTALL_BINDIR
* fix: Add a patch to avoid power throttling API on non-msvc windows builds
* fix: Sync patch changes for ggml-cpu.c
* feat: Bump llama.cpp to 4a4f42
This picks up support for Kimi K2 and PLaMO-2
* feat: Sync llama.cpp
* fix: Handle multi-chunk image encodings from mtmd
* fix: Re-number patches after merge with `main`
* feat: Bump to 41e78c in the makefile
* fix: Fix Solar and argsort/copy patches after bump
* fix: Remove Gemma3n CUDA Graphs patch
It was implemented upstream:
https://github.com/ggml-org/llama.cpp/pull/14741
* feat: Sync llama.cpp / ggml after latest bump
* build: Remove unnecessary CFLAGS definitions in cpu.go
* fix: Remove unnecessary additions in the rsync-filter
* fix: Remove unused vendored code for chat template parsing
* Revert "fix: Remove Gemma3n CUDA Graphs patch"
This reverts commit d724caced3ce21f08924d4b7801f94ce6638f6ea.
* fix: Update 0020 CUDA Graphs for gemma3n to keep both llama.cpp and ollama fixes
https://github.com/ollama/ollama/pull/11195#issuecomment-3137312394
* fix: Sync ggml-cuda.cu after keeping both style cuda graph fixes for gemma3n
* unwind mxfp4 patch
Prepare to bump ggml with their impl for mxfp4
* bump
* fix windows build error
* Convert tensors at load time
Repack the mxfp4 tensors as ggmls kernels expect them to be.
* convert mlp bf16 to f32
* buffer the conversion better
* reshape earlier
* openai swiglu
* add ids
* split qkv, gate_up
* fix nested alt tags
* fast attention
* remove debug messages
* fix lint
* remove redundant test
* remap values only if source/target are different
* add back i32->i32 copy
* refactor cpu quants
* clean up vendor
* update patch instructions
* clean up patches
* remove webgpu
* update mem
* also handle gpt-oss
* revert convert changes
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
This commit is contained in:
Michael Yang
212
llama/llama.cpp/src/unicode.cpp
vendored
212
llama/llama.cpp/src/unicode.cpp
vendored
@@ -224,12 +224,17 @@ static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
|
||||
// disable C++17 deprecation warning for std::codecvt_utf8
|
||||
# pragma clang diagnostic push
|
||||
# pragma clang diagnostic ignored "-Wdeprecated-declarations"
|
||||
#elif defined(__GNUC__)
|
||||
# pragma GCC diagnostic push
|
||||
# pragma GCC diagnostic ignored "-Wdeprecated-declarations"
|
||||
#endif
|
||||
|
||||
std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;
|
||||
|
||||
#if defined(__clang__)
|
||||
# pragma clang diagnostic pop
|
||||
#elif defined(__GNUC__)
|
||||
# pragma GCC diagnostic pop
|
||||
#endif
|
||||
|
||||
return conv.from_bytes(s);
|
||||
@@ -573,6 +578,178 @@ static std::vector<size_t> unicode_regex_split_stl(const std::string & text, con
|
||||
return bpe_offsets;
|
||||
}
|
||||
|
||||
// K2 system regex patterns (from tokenization_kimi.py):
|
||||
// [\p{Han}]+|[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?|[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+
|
||||
static std::vector<size_t> unicode_regex_split_custom_kimi_k2(const std::string & text, const std::vector<size_t> & offsets) {
|
||||
std::vector<size_t> bpe_offsets;
|
||||
bpe_offsets.reserve(offsets.size());
|
||||
|
||||
const auto cpts = unicode_cpts_from_utf8(text);
|
||||
|
||||
size_t start = 0;
|
||||
for (auto offset : offsets) {
|
||||
const size_t offset_ini = start;
|
||||
const size_t offset_end = start + offset;
|
||||
assert(offset_end <= cpts.size());
|
||||
start = offset_end;
|
||||
|
||||
static const uint32_t OUT_OF_RANGE = 0xFFFFFFFF;
|
||||
auto _get_cpt = [&] (const size_t pos) -> uint32_t {
|
||||
return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
|
||||
};
|
||||
|
||||
auto _get_flags = [&] (const size_t pos) -> unicode_cpt_flags {
|
||||
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags_from_cpt(cpts[pos]) : unicode_cpt_flags{};
|
||||
};
|
||||
|
||||
size_t _prev_end = offset_ini;
|
||||
auto _add_token = [&] (const size_t end) -> size_t {
|
||||
assert(_prev_end <= end && end <= offset_end);
|
||||
size_t len = end - _prev_end;
|
||||
if (len > 0) {
|
||||
bpe_offsets.push_back(len);
|
||||
}
|
||||
_prev_end = end;
|
||||
return len;
|
||||
};
|
||||
|
||||
for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
|
||||
const uint32_t cpt = _get_cpt(pos);
|
||||
const auto flags = _get_flags(pos);
|
||||
|
||||
// Pattern 1: [\p{Han}]+ (Chinese characters)
|
||||
if (unicode_cpt_is_han(cpt)) {
|
||||
while (unicode_cpt_is_han(_get_cpt(pos))) {
|
||||
pos++;
|
||||
}
|
||||
_add_token(pos);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Pattern 2 & 3: Letter words excluding Han characters with optional contractions
|
||||
// [^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+(?:'s|'t|'re|'ve|'m|'ll|'d)?
|
||||
// [^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*(?:'s|'t|'re|'ve|'m|'ll|'d)?
|
||||
// Check if current char is a letter OR if current char could be a leading char and next char is a letter
|
||||
bool is_letter_pattern = (flags.is_letter && !unicode_cpt_is_han(cpt)) ||
|
||||
(!(cpt == '\r' || cpt == '\n' || flags.is_letter || flags.is_number) &&
|
||||
_get_flags(pos + 1).is_letter && !unicode_cpt_is_han(_get_cpt(pos + 1)));
|
||||
|
||||
if (is_letter_pattern) {
|
||||
// Handle optional leading non-letter/non-number character
|
||||
bool has_leading_char = false;
|
||||
if (!(cpt == '\r' || cpt == '\n' || flags.is_letter || flags.is_number)) {
|
||||
has_leading_char = true;
|
||||
pos++;
|
||||
}
|
||||
|
||||
// Match letter sequence (excluding Han characters)
|
||||
bool has_letters = false;
|
||||
while (_get_flags(pos).is_letter && !unicode_cpt_is_han(_get_cpt(pos))) {
|
||||
has_letters = true;
|
||||
pos++;
|
||||
}
|
||||
|
||||
// Only proceed if we found letters (after potentially skipping leading char)
|
||||
if (has_letters || (!has_leading_char && _get_flags(pos).is_letter && !unicode_cpt_is_han(_get_cpt(pos)))) {
|
||||
if (!has_letters) pos++; // consume the first letter if we didn't already
|
||||
|
||||
// Continue consuming letters
|
||||
while (_get_flags(pos).is_letter && !unicode_cpt_is_han(_get_cpt(pos))) {
|
||||
pos++;
|
||||
}
|
||||
|
||||
// Check for optional contractions (?:'s|'t|'re|'ve|'m|'ll|'d)
|
||||
if (_get_cpt(pos) == '\'' && pos + 1 < offset_end) {
|
||||
uint32_t cpt_next = unicode_tolower(_get_cpt(pos + 1));
|
||||
if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
|
||||
pos += 2;
|
||||
} else if (pos + 2 < offset_end) {
|
||||
uint32_t cpt_next_next = unicode_tolower(_get_cpt(pos + 2));
|
||||
if ((cpt_next == 'r' && cpt_next_next == 'e') ||
|
||||
(cpt_next == 'v' && cpt_next_next == 'e') ||
|
||||
(cpt_next == 'l' && cpt_next_next == 'l')) {
|
||||
pos += 3;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
_add_token(pos);
|
||||
continue;
|
||||
} else if (has_leading_char) {
|
||||
// We consumed a leading char but found no letters, backtrack
|
||||
pos--;
|
||||
}
|
||||
}
|
||||
|
||||
// Pattern 4: \p{N}{1,3} (numbers 1-3 digits)
|
||||
if (flags.is_number) {
|
||||
size_t ini = pos;
|
||||
while (_get_flags(pos).is_number) {
|
||||
if (++pos - ini >= 3) {
|
||||
_add_token(pos);
|
||||
ini = pos;
|
||||
}
|
||||
}
|
||||
_add_token(pos);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Pattern 5: ?[^\s\p{L}\p{N}]+[\r\n]* (optional space + non-word chars + optional newlines)
|
||||
auto flags2 = (cpt == ' ' ? _get_flags(pos + 1) : flags);
|
||||
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number) && flags2.as_uint()) {
|
||||
pos += (cpt == ' ');
|
||||
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number) && flags2.as_uint()) {
|
||||
flags2 = _get_flags(++pos);
|
||||
}
|
||||
// Match optional [\r\n]*
|
||||
uint32_t cpt2 = _get_cpt(pos);
|
||||
while (cpt2 == '\r' || cpt2 == '\n') {
|
||||
cpt2 = _get_cpt(++pos);
|
||||
}
|
||||
_add_token(pos);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Count whitespace characters
|
||||
size_t num_whitespaces = 0;
|
||||
size_t last_end_r_or_n = 0;
|
||||
while (_get_flags(pos + num_whitespaces).is_whitespace) {
|
||||
uint32_t cpt2 = _get_cpt(pos + num_whitespaces);
|
||||
if (cpt2 == '\r' || cpt2 == '\n') {
|
||||
last_end_r_or_n = pos + num_whitespaces + 1;
|
||||
}
|
||||
num_whitespaces++;
|
||||
}
|
||||
|
||||
// Pattern 6: \s*[\r\n]+ (whitespace with newlines)
|
||||
if (last_end_r_or_n > 0) {
|
||||
pos = last_end_r_or_n;
|
||||
_add_token(pos);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Pattern 7: \s+(?!\S) (trailing whitespace)
|
||||
if (num_whitespaces > 1 && _get_cpt(pos + num_whitespaces) != OUT_OF_RANGE) {
|
||||
pos += num_whitespaces - 1;
|
||||
_add_token(pos);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Pattern 8: \s+ (general whitespace)
|
||||
if (num_whitespaces > 0) {
|
||||
pos += num_whitespaces;
|
||||
_add_token(pos);
|
||||
continue;
|
||||
}
|
||||
|
||||
// No matches - consume single character
|
||||
_add_token(++pos);
|
||||
}
|
||||
}
|
||||
|
||||
return bpe_offsets;
|
||||
}
|
||||
|
||||
static std::vector<size_t> unicode_regex_split_custom(const std::string & text, const std::string & regex_expr, const std::vector<size_t> & offsets) {
|
||||
std::vector<size_t> bpe_offsets;
|
||||
|
||||
@@ -583,6 +760,9 @@ static std::vector<size_t> unicode_regex_split_custom(const std::string & text,
|
||||
regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
|
||||
|
||||
bpe_offsets = unicode_regex_split_custom_llama3(text, offsets);
|
||||
} else if (regex_expr == "\\p{Han}+") {
|
||||
// K2's first pattern - handle all K2 patterns together
|
||||
bpe_offsets = unicode_regex_split_custom_kimi_k2(text, offsets);
|
||||
}
|
||||
|
||||
return bpe_offsets;
|
||||
@@ -688,6 +868,38 @@ uint32_t unicode_tolower(uint32_t cpt) {
|
||||
return cpt; // Return the original code point if no lowercase mapping is found
|
||||
}
|
||||
|
||||
bool unicode_cpt_is_han(uint32_t cpt) {
|
||||
// Han character ranges (Chinese/CJK characters)
|
||||
// CJK Unified Ideographs (most common)
|
||||
if (cpt >= 0x4E00 && cpt <= 0x9FFF) return true;
|
||||
|
||||
// CJK Extension A
|
||||
if (cpt >= 0x3400 && cpt <= 0x4DBF) return true;
|
||||
|
||||
// CJK Extension B
|
||||
if (cpt >= 0x20000 && cpt <= 0x2A6DF) return true;
|
||||
|
||||
// CJK Extension C
|
||||
if (cpt >= 0x2A700 && cpt <= 0x2B73F) return true;
|
||||
|
||||
// CJK Extension D
|
||||
if (cpt >= 0x2B740 && cpt <= 0x2B81F) return true;
|
||||
|
||||
// CJK Extension E
|
||||
if (cpt >= 0x2B820 && cpt <= 0x2CEAF) return true;
|
||||
|
||||
// CJK Extension F
|
||||
if (cpt >= 0x2CEB0 && cpt <= 0x2EBEF) return true;
|
||||
|
||||
// CJK Compatibility Ideographs
|
||||
if (cpt >= 0xF900 && cpt <= 0xFAFF) return true;
|
||||
|
||||
// CJK Compatibility Ideographs Supplement
|
||||
if (cpt >= 0x2F800 && cpt <= 0x2FA1F) return true;
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs) {
|
||||
// unicode categories
|
||||
static const std::map<std::string, int> k_ucat_enum = {
|
||||
|
||||
Reference in New Issue
Block a user