mirror of
https://github.com/ollama/ollama.git
synced 2026-07-23 09:10:53 -05:00
25223160d8
Older Ollama builds ship GGUFs that diverge slightly from upstream llama.cpp
in arch names, KV keys, tensor names, and (for vision models) file layout
(text+vision in one monolithic file). This adds a self-contained compat
layer that translates those files in memory at load time, so
~/.ollama/models/blobs/* can be served by upstream llama-server with no
re-conversion and no re-download.
Structure:
llama/compat/
llama-ollama-compat.{h,cpp} — the shim (Ollama-owned, ~500 LOC)
upstream-edits.patch — ~48 lines of call-site hooks in 6 upstream files
compat.cmake — include()-able CMake fragment
README.md — what/why/how-to-regen
Integration: llama/server/CMakeLists.txt includes compat.cmake and passes
OLLAMA_LLAMA_CPP_COMPAT_PATCH_COMMAND to FetchContent_Declare via
PATCH_COMMAND. When OLLAMA_LLAMA_CPP_SOURCE is set (dev mode), the patch is
skipped so the developer's tree stays untouched.
Currently handles gemma3 (text + vision). Pattern is data-driven — adding
other archs is a new handle_<arch>() + one dispatch line. See README for
the per-arch checklist.
Verified end-to-end: `llama-server --model BLOB --mmproj BLOB` with an
Ollama gemma3:latest blob answers both text prompts ("Paris") and vision
prompts (correct image descriptions).
162 lines
6.9 KiB
Diff
162 lines
6.9 KiB
Diff
diff --git a/ggml/include/gguf.h b/ggml/include/gguf.h
|
|
index 02d5f221c..2f64264f4 100644
|
|
--- a/ggml/include/gguf.h
|
|
+++ b/ggml/include/gguf.h
|
|
@@ -162,6 +162,9 @@ extern "C" {
|
|
// assumes that at least gguf_get_tensor_size bytes can be read from data
|
|
GGML_API void gguf_set_tensor_data(struct gguf_context * ctx, const char * name, const void * data);
|
|
|
|
+ // rename a tensor. Returns false if old_name is not present.
|
|
+ GGML_API bool gguf_rename_tensor(struct gguf_context * ctx, const char * old_name, const char * new_name);
|
|
+
|
|
// writing gguf files can be done in 3 ways:
|
|
//
|
|
// - write the entire gguf_context to a binary file in a single pass:
|
|
diff --git a/ggml/src/gguf.cpp b/ggml/src/gguf.cpp
|
|
index ab3cc9748..e3d06c959 100644
|
|
--- a/ggml/src/gguf.cpp
|
|
+++ b/ggml/src/gguf.cpp
|
|
@@ -1280,6 +1280,16 @@ void gguf_set_tensor_data(struct gguf_context * ctx, const char * name, const vo
|
|
ctx->info[tensor_id].t.data = (void *)(uintptr_t)data; // double cast suppresses warning about casting away const
|
|
}
|
|
|
|
+bool gguf_rename_tensor(struct gguf_context * ctx, const char * old_name, const char * new_name) {
|
|
+ const int64_t tensor_id = gguf_find_tensor(ctx, old_name);
|
|
+ if (tensor_id < 0) {
|
|
+ return false;
|
|
+ }
|
|
+ // ggml_set_name truncates to GGML_MAX_NAME.
|
|
+ ggml_set_name(&ctx->info[tensor_id].t, new_name);
|
|
+ return true;
|
|
+}
|
|
+
|
|
struct gguf_writer_base {
|
|
size_t written_bytes {0u};
|
|
|
|
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
|
|
index 7b1fcfca0..155a819fa 100644
|
|
--- a/src/CMakeLists.txt
|
|
+++ b/src/CMakeLists.txt
|
|
@@ -32,6 +32,7 @@ add_library(llama
|
|
llama-model-loader.cpp
|
|
llama-model-saver.cpp
|
|
llama-model.cpp
|
|
+ llama-ollama-compat.cpp
|
|
llama-quant.cpp
|
|
llama-sampler.cpp
|
|
llama-vocab.cpp
|
|
diff --git a/src/llama-model-loader.cpp b/src/llama-model-loader.cpp
|
|
index 4e65a45a5..75836c683 100644
|
|
--- a/src/llama-model-loader.cpp
|
|
+++ b/src/llama-model-loader.cpp
|
|
@@ -4,6 +4,7 @@
|
|
#include "ggml.h"
|
|
#include "gguf.h"
|
|
#include "llama-hparams.h"
|
|
+#include "llama-ollama-compat.h"
|
|
|
|
#include <algorithm>
|
|
#include <array>
|
|
@@ -549,6 +550,7 @@ llama_model_loader::llama_model_loader(
|
|
}
|
|
|
|
get_key(llm_kv(LLM_KV_GENERAL_ARCHITECTURE), arch_name, false);
|
|
+ llama_ollama_compat::translate_metadata(this, metadata, ctx, arch_name);
|
|
llm_kv = LLM_KV(llm_arch_from_string(arch_name));
|
|
|
|
files.emplace_back(new llama_file(fname.c_str(), "rb", use_direct_io));
|
|
@@ -573,6 +575,9 @@ llama_model_loader::llama_model_loader(
|
|
// so we build a unified tensors index for weights.
|
|
for (ggml_tensor * cur = ggml_get_first_tensor(ctx); cur; cur = ggml_get_next_tensor(ctx, cur)) {
|
|
std::string tensor_name = std::string(cur->name);
|
|
+ if (llama_ollama_compat::should_skip_tensor(this, tensor_name.c_str())) {
|
|
+ continue;
|
|
+ }
|
|
// make sure there is no duplicated tensor names
|
|
if (weights_map.find(tensor_name) != weights_map.end()) {
|
|
throw std::runtime_error(format("invalid model: tensor '%s' is duplicated", ggml_get_name(cur)));
|
|
@@ -683,6 +688,9 @@ llama_model_loader::llama_model_loader(
|
|
// Save tensors data offset info of the main file.
|
|
for (ggml_tensor * cur = ggml_get_first_tensor(ctx); cur; cur = ggml_get_next_tensor(ctx, cur)) {
|
|
std::string tensor_name = std::string(cur->name);
|
|
+ if (llama_ollama_compat::should_skip_tensor(this, tensor_name.c_str())) {
|
|
+ continue;
|
|
+ }
|
|
// make sure there is no duplicated tensor names
|
|
if (weights_map.find(tensor_name) != weights_map.end()) {
|
|
throw std::runtime_error(format("invalid model: tensor '%s' is duplicated", ggml_get_name(cur)));
|
|
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
|
|
index 4ded484dd..7d3509c23 100644
|
|
--- a/src/llama-model.cpp
|
|
+++ b/src/llama-model.cpp
|
|
@@ -6,6 +6,7 @@
|
|
#include "llama-mmap.h"
|
|
#include "llama-cparams.h"
|
|
#include "llama-model-loader.h"
|
|
+#include "llama-ollama-compat.h"
|
|
|
|
#include "llama-kv-cache.h"
|
|
#include "llama-kv-cache-iswa.h"
|
|
@@ -8023,6 +8024,9 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
|
|
if (!ml.load_all_data(ctx, buf_map, use_mlock ? &pimpl->mlock_mmaps : NULL, params.progress_callback, params.progress_callback_user_data)) {
|
|
return false;
|
|
}
|
|
+ // Apply any Ollama-format numerical fixups (e.g. gemma3 RMSNorm +1)
|
|
+ // while the data is in its final backend buffers.
|
|
+ llama_ollama_compat::apply_tensor_transforms(&ml, ctx);
|
|
}
|
|
|
|
if (use_mmap_buffer) {
|
|
diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
|
|
index f0e8786b6..ec2a7d320 100644
|
|
--- a/tools/mtmd/clip.cpp
|
|
+++ b/tools/mtmd/clip.cpp
|
|
@@ -10,6 +10,8 @@
|
|
#include "ggml-backend.h"
|
|
#include "gguf.h"
|
|
|
|
+#include "src/llama-ollama-compat.h"
|
|
+
|
|
#include <algorithm>
|
|
#include <cassert>
|
|
#include <cmath>
|
|
@@ -985,6 +987,11 @@ struct clip_model_loader {
|
|
|
|
ctx_meta.reset(meta);
|
|
|
|
+ // If this is an Ollama-format monolithic GGUF (text + embedded
|
|
+ // vision), translate its metadata and tensor names into the
|
|
+ // upstream mmproj shape so the rest of this loader runs unchanged.
|
|
+ llama_ollama_compat::translate_clip_metadata(ctx_gguf.get(), meta);
|
|
+
|
|
const int n_tensors = gguf_get_n_tensors(ctx_gguf.get());
|
|
|
|
// print gguf info
|
|
@@ -2358,11 +2365,25 @@ struct clip_model_loader {
|
|
auto it_off = tensor_offset.find(t->name);
|
|
GGML_ASSERT(it_off != tensor_offset.end() && "no offset for tensor");
|
|
const size_t offset = it_off->second;
|
|
+ size_t num_bytes = ggml_nbytes(cur);
|
|
+
|
|
+ // Ollama-compat: let the compat layer supply promoted tensor
|
|
+ // data (e.g. F16→F32 for conv weights) instead of reading
|
|
+ // bytes directly from the file.
|
|
+ std::vector<uint8_t> compat_buf;
|
|
+ if (llama_ollama_compat::supply_promoted_tensor_data(cur, fname.c_str(), offset, compat_buf)) {
|
|
+ if (ggml_backend_buft_is_host(buft)) {
|
|
+ std::memcpy(cur->data, compat_buf.data(), num_bytes);
|
|
+ } else {
|
|
+ ggml_backend_tensor_set(cur, compat_buf.data(), 0, num_bytes);
|
|
+ }
|
|
+ continue;
|
|
+ }
|
|
+
|
|
fin.seekg(offset, std::ios::beg);
|
|
if (!fin) {
|
|
throw std::runtime_error(string_format("%s: failed to seek for tensor %s\n", __func__, t->name));
|
|
}
|
|
- size_t num_bytes = ggml_nbytes(cur);
|
|
if (ggml_backend_buft_is_host(buft)) {
|
|
// for the CPU and Metal backend, we can read directly into the tensor
|
|
fin.read(reinterpret_cast<char *>(cur->data), num_bytes);
|