popov/neuron-tai
1
0
Fork 0
Code Issues 42 Pull Requests Actions Packages Projects Releases Wiki Activity

story: DGR-034 Implement dense-Llama range-aware GGUF ownership

Browse Source
This commit is contained in:
Dobromir Popov
2026-08-01 01:08:28 +03:00
parent 27a0d89678
commit d339cfde25
18 changed files with 1393 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/node/native/llama/PATCH-STACK.md
View File

@@ -28,6 +28,12 @@ One numbered patch per concern (ADR-0024 local seams only):
5. `0005-worker-range-report-hook.patch` (worker hooks) exposes the
`llama_model_meshnet_range_report` C API the project-owned worker binds to
and registers a model-free native fixture test for it.
6. `0006-meshnet-range-report-tool.patch` (range reporting) adds the
project-owned `meshnet-range-report` tool: it loads one GGUF artifact
through the owned-range loader and prints a JSON document derived from the
loaded model state — the owned-range report, the registered tensor set
audited against the requested ownership, and backend-buffer byte counts.
It never builds or runs a compute graph.
Meshnet routing, Tracker, gRPC, relay, billing, authentication, and telemetry
remain outside this directory; the stack is checked for such control-plane

14
packages/node/native/llama/UPSTREAM_LOCK.json
View File

@@ -10,21 +10,23 @@
"method": "git-clone-detached-commit",
"workspace": "build/llama.cpp"
},
"patched_tree": "c0045714735ae5ee7b7334a480d8ac04e03e1b18",
"patched_tree": "8f7e87fea6743f0b9744afe44f9e6f9ca3b7d08a",
"upstream_license": "MIT",
"patch_series": [
"0001-cmake-reserve-meshnet-patch-stack-abi-marker.patch",
"0002-dense-llama-owned-range-loading.patch",
"0003-owned-range-filtered-state-report.patch",
"0004-dense-boundary-io-endpoint-guard.patch",
"0005-worker-range-report-hook.patch"
"0005-worker-range-report-hook.patch",
"0006-meshnet-range-report-tool.patch"
],
"patch_scope": [
"Reserved CMake ABI marker only; no execution or model semantics.",
"Range loading: dense-Llama owned-range params, validation, and filtered tensor registration with endpoint ownership.",
"Filtered state: owned-range report populated from registered tensors and backend buffers, derived never asserted.",
"Boundary I/O: endpoint ownership flags and a fail-closed dense graph guard until typed endpoint adapters exist.",
"Worker hooks: public C range-report API and the model-free native fixture test the project-owned worker binds to."
"Worker hooks: public C range-report API and the model-free native fixture test the project-owned worker binds to.",
"Range reporting: project-owned tool that loads one artifact through the owned-range loader and reports derived ownership and buffer-byte state as JSON."
],
"patch_assumptions": "patches/UPSTREAM-ASSUMPTIONS.json",
"build": {
@@ -46,7 +48,7 @@
"-DGGML_VULKAN=OFF",
"-DGGML_METAL=OFF"
],
"native_targets": ["llama-gguf-hash", "test-meshnet-range-ownership"],
"native_targets": ["llama-gguf-hash", "test-meshnet-range-ownership", "meshnet-range-report"],
"smoke_binary": "bin/llama-gguf-hash",
"smoke_args": ["--help"],
"smoke_output_token": "usage",
@@ -81,7 +83,9 @@
"src/llama-model.h",
"src/models/llama.cpp",
"tests/CMakeLists.txt",
"tests/test-meshnet-range-ownership.cpp"
"tests/test-meshnet-range-ownership.cpp",
"tools/meshnet-range-report/CMakeLists.txt",
"tools/meshnet-range-report/meshnet-range-report.cpp"
],
"stock_glm_limitations": "This pin may load GLM-5.2 through the dense-MLA compatibility fallback. It does not prove native DSA, IndexShare, MoE semantic correctness, numerical equivalence, performance, or route certification."
}

414
packages/node/native/llama/patches/0006-meshnet-range-report-tool.patch Normal file
View File

@@ -0,0 +1,414 @@
From: Meshnet <meshnet@invalid>
Subject: [PATCH] llama: add dense-Llama owned-range report tool
Concern: range reporting. Adds the project-owned meshnet-range-report tool:
it loads one GGUF artifact through the Meshnet owned-range loader and prints
a JSON document derived from the loaded model state — the owned-range
report, the registered tensor set audited against the requested ownership,
and backend-buffer byte counts (optionally split from repack buffers, plus
process resident readings). It never builds or runs a compute graph and
never trusts caller-asserted range or endpoint claims.
---
diff --git a/CMakeLists.txt b/CMakeLists.txt
index a9afcff..868793b 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -281,3 +281,6 @@ configure_file(cmake/llama.pc.in
install(FILES "${CMAKE_CURRENT_BINARY_DIR}/llama.pc"
DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
+
+# Meshnet-owned owned-range report tool (patch stack, range-report concern).
+add_subdirectory(tools/meshnet-range-report)
diff --git a/tools/meshnet-range-report/CMakeLists.txt b/tools/meshnet-range-report/CMakeLists.txt
new file mode 100644
index 000000000..24401007e
--- /dev/null
+++ b/tools/meshnet-range-report/CMakeLists.txt
@@ -0,0 +1,7 @@
+# Meshnet-owned dense-Llama owned-range load/report tool.
+#
+# Built unconditionally with the patched tree: it exercises the Meshnet
+# owned-range loader against real GGUF artifacts and reports only state
+# derived from the loaded model (registered tensors, backend buffers).
+add_executable(meshnet-range-report meshnet-range-report.cpp)
+target_link_libraries(meshnet-range-report PRIVATE llama)
diff --git a/tools/meshnet-range-report/meshnet-range-report.cpp b/tools/meshnet-range-report/meshnet-range-report.cpp
new file mode 100644
index 000000000..49a5eb2a0
--- /dev/null
+++ b/tools/meshnet-range-report/meshnet-range-report.cpp
@@ -0,0 +1,373 @@
+// Meshnet-owned dense-Llama owned-range load/report tool.
+//
+// Loads one GGUF artifact through the Meshnet owned-range loader
+// (llama_model_params::meshnet_owned_layer_start/end) and prints a single
+// JSON report derived from the loaded model state — registered tensors and
+// backend buffers, never caller-asserted values. The audit fails closed when
+// the registered tensor set disagrees with the requested ownership: every
+// registered per-layer tensor must lie inside [start, end), the token
+// embedding may be registered only by the head shard (start == 0) or by a
+// tail shard whose model ties the output head to the embedding, and the
+// final norm plus output head may be registered only by the tail shard
+// (end == n_layer).
+
+#include "ggml.h"
+#include "llama.h"
+
+#include "../../src/llama-model.h"
+
+#include <cstdint>
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
+#include <set>
+#include <string>
+#include <sys/stat.h>
+#include <vector>
+
+namespace {
+
+constexpr int kExitUsage = 2;
+constexpr int kExitLoad = 3;
+constexpr int kExitAudit = 4;
+
+std::string g_log_tail;
+
+void capture_log(enum ggml_log_level level, const char * text, void *) {
+ if (level >= GGML_LOG_LEVEL_ERROR) {
+ g_log_tail += text;
+ if (g_log_tail.size() > 512) {
+ g_log_tail.erase(0, g_log_tail.size() - 512);
+ }
+ }
+}
+
+std::string json_escape(const std::string & value) {
+ std::string out;
+ for (const char c : value) {
+ if (c == '"' || c == '\\') {
+ out += '\\';
+ out += c;
+ } else if (c == '\n') {
+ out += "\\n";
+ } else if (c == '\r') {
+ // drop carriage returns from embedded log text
+ } else {
+ out += c;
+ }
+ }
+ return out;
+}
+
+std::string json_string_array(const std::vector<std::string> & items) {
+ std::string out = "[";
+ for (size_t i = 0; i < items.size(); ++i) {
+ if (i) {
+ out += ", ";
+ }
+ out += "\"" + json_escape(items[i]) + "\"";
+ }
+ return out + "]";
+}
+
+std::string json_int_array(const std::vector<int> & items) {
+ std::string out = "[";
+ for (size_t i = 0; i < items.size(); ++i) {
+ if (i) {
+ out += ", ";
+ }
+ out += std::to_string(items[i]);
+ }
+ return out + "]";
+}
+
+int fail(int code, const std::string & error) {
+ std::string detail = error;
+ if (!g_log_tail.empty()) {
+ detail += ": " + g_log_tail;
+ }
+ std::printf("{\"ok\": false, \"error\": \"%s\"}\n", json_escape(detail).c_str());
+ return code;
+}
+
+bool parse_nonnegative(const char * text, int & out) {
+ if (text == nullptr || *text == '\0' || *text == '-') {
+ return false;
+ }
+ char * end = nullptr;
+ const long value = std::strtol(text, &end, 10);
+ if (end == text || *end != '\0' || value > INT32_MAX) {
+ return false;
+ }
+ out = static_cast<int>(value);
+ return true;
+}
+
+uint64_t file_size(const std::string & path) {
+ struct stat st;
+ return ::stat(path.c_str(), &st) == 0 ? static_cast<uint64_t>(st.st_size) : 0;
+}
+
+struct proc_status {
+ uint64_t vm_size = 0;
+ uint64_t vm_rss = 0;
+ uint64_t vm_hwm = 0;
+ bool valid = false;
+};
+
+proc_status read_proc_status() {
+ proc_status out;
+#ifdef __linux__
+ FILE * f = std::fopen("/proc/self/status", "r");
+ if (!f) {
+ return out;
+ }
+ char line[256];
+ while (std::fgets(line, sizeof(line), f)) {
+ uint64_t kb = 0;
+ if (std::sscanf(line, "VmSize: %lu kB", &kb) == 1) {
+ out.vm_size = kb * 1024;
+ } else if (std::sscanf(line, "VmRSS: %lu kB", &kb) == 1) {
+ out.vm_rss = kb * 1024;
+ } else if (std::sscanf(line, "VmHWM: %lu kB", &kb) == 1) {
+ out.vm_hwm = kb * 1024;
+ }
+ }
+ std::fclose(f);
+ out.valid = true;
+#endif
+ return out;
+}
+
+void usage(const char * argv0) {
+ std::fprintf(stderr,
+ "usage: %s --model PATH --start N --end M [--no-mmap] [--no-extra-bufts] [--touch]\n"
+ "loads one dense-Llama GGUF through the Meshnet owned-range loader and\n"
+ "prints a JSON report derived from the loaded model state\n",
+ argv0);
+}
+
+} // namespace
+
+int main(int argc, char ** argv) {
+ std::string model_path;
+ int start = -1;
+ int end = -1;
+ bool use_mmap = true;
+ bool use_extra_bufts = true;
+ bool touch = false;
+
+ for (int i = 1; i < argc; ++i) {
+ const std::string arg = argv[i];
+ if (arg == "--model" && i + 1 < argc) {
+ model_path = argv[++i];
+ } else if (arg == "--start" && i + 1 < argc) {
+ if (!parse_nonnegative(argv[++i], start)) {
+ usage(argv[0]);
+ return kExitUsage;
+ }
+ } else if (arg == "--end" && i + 1 < argc) {
+ if (!parse_nonnegative(argv[++i], end)) {
+ usage(argv[0]);
+ return kExitUsage;
+ }
+ } else if (arg == "--no-mmap") {
+ use_mmap = false;
+ } else if (arg == "--no-extra-bufts") {
+ use_extra_bufts = false;
+ } else if (arg == "--touch") {
+ touch = true;
+ } else {
+ usage(argv[0]);
+ return kExitUsage;
+ }
+ }
+ if (model_path.empty() || start < 0 || end < 0) {
+ usage(argv[0]);
+ return kExitUsage;
+ }
+
+ llama_log_set(capture_log, nullptr);
+ llama_backend_init();
+
+ llama_model_params params = llama_model_default_params();
+ params.meshnet_owned_layer_start = start;
+ params.meshnet_owned_layer_end = end;
+ params.use_mmap = use_mmap;
+ params.use_extra_bufts = use_extra_bufts;
+ params.progress_callback = nullptr;
+
+ llama_model * model = llama_model_load_from_file(model_path.c_str(), params);
+ if (model == nullptr) {
+ return fail(kExitLoad, "owned-range load rejected the artifact or range");
+ }
+
+ llama_meshnet_range_report report = {};
+ if (!llama_model_meshnet_range_report(model, &report)) {
+ llama_model_free(model);
+ return fail(kExitLoad, "loaded model carries no owned-range report");
+ }
+
+ char arch_buf[128] = {};
+ std::string arch;
+ if (llama_model_meta_val_str(model, "general.architecture", arch_buf, sizeof(arch_buf)) >= 0) {
+ arch = arch_buf;
+ }
+ const int n_layer = llama_model_n_layer(model);
+ const uint64_t bytes_on_disk = file_size(model_path);
+
+ // Audit the registered tensor set against the requested ownership.
+ const auto & tensors = llama_internal_get_tensor_map(model);
+ bool has_embd = false;
+ bool has_out_norm = false;
+ bool has_out = false;
+ std::set<int> owned_layers;
+ std::vector<std::string> unexpected;
+ uint64_t registered_bytes = 0;
+ for (const auto & entry : tensors) {
+ const std::string & name = entry.first;
+ registered_bytes += ggml_nbytes(entry.second);
+ if (name == "token_embd.weight") {
+ has_embd = true;
+ continue;
+ }
+ if (name == "output_norm.weight") {
+ has_out_norm = true;
+ continue;
+ }
+ if (name == "output.weight") {
+ has_out = true;
+ continue;
+ }
+ int block = -1;
+ if (std::sscanf(name.c_str(), "blk.%d.", &block) == 1 && block >= 0) {
+ owned_layers.insert(block);
+ continue;
+ }
+ unexpected.push_back(name);
+ }
+
+ // A tail shard whose model ties the output head to the token embedding
+ // registers token_embd.weight as its output head instead of output.weight.
+ const bool tied_tail = end == n_layer && has_embd && !has_out;
+ const bool expect_embd = start == 0 || tied_tail;
+
+ std::vector<int> missing_layers;
+ for (int i = start; i < end; ++i) {
+ if (!owned_layers.count(i)) {
+ missing_layers.push_back(i);
+ }
+ }
+ std::vector<int> outside_layers;
+ for (const int block : owned_layers) {
+ if (block < start || block >= end) {
+ outside_layers.push_back(block);
+ }
+ }
+
+ std::vector<std::string> mismatches;
+ if (report.start_layer != start || report.end_layer != end) {
+ mismatches.push_back("reported range differs from the requested range");
+ }
+ if (has_embd != expect_embd) {
+ mismatches.push_back("token-embedding registration disagrees with endpoint ownership");
+ }
+ if ((end == n_layer) && !has_out_norm) {
+ mismatches.push_back("tail range is missing the final norm");
+ }
+ if ((end == n_layer) && !has_out && !has_embd) {
+ mismatches.push_back("tail range is missing the output head");
+ }
+ if ((end != n_layer) && (has_out_norm || has_out)) {
+ mismatches.push_back("non-tail range registered tail-only tensors");
+ }
+ if (report.has_token_embeddings != has_embd) {
+ mismatches.push_back("reported embedding ownership disagrees with registered tensors");
+ }
+ if (report.has_output_head != (end == n_layer)) {
+ mismatches.push_back("reported output-head ownership disagrees with endpoint ownership");
+ }
+ if (!missing_layers.empty()) {
+ mismatches.push_back("owned range has missing per-layer tensors");
+ }
+ if (!outside_layers.empty()) {
+ mismatches.push_back("registered per-layer tensors lie outside the owned range");
+ }
+ if (!unexpected.empty()) {
+ mismatches.push_back("registered tensors outside the dense-Llama ownership vocabulary");
+ }
+ if (use_mmap && report.mapped_bytes < registered_bytes) {
+ mismatches.push_back("mapped span undercounts the registered tensors");
+ }
+ if (!use_mmap && report.resident_bytes < registered_bytes) {
+ mismatches.push_back("resident allocation undercounts the registered tensors");
+ }
+
+ if (touch) {
+ volatile uint64_t sink = 0;
+ for (const auto & entry : tensors) {
+ const auto * data = static_cast<const volatile uint8_t *>(entry.second->data);
+ const size_t nbytes = ggml_nbytes(entry.second);
+ for (size_t i = 0; i < nbytes; i += 4096) {
+ sink += data[i];
+ }
+ }
+ (void) sink;
+ }
+
+ const proc_status proc = read_proc_status();
+
+ if (!mismatches.empty()) {
+ llama_model_free(model);
+ return fail(kExitAudit, "ownership audit failed: " + json_string_array(mismatches));
+ }
+
+ std::printf(
+ "{\n"
+ " \"ok\": true,\n"
+ " \"model\": \"%s\",\n"
+ " \"architecture\": \"%s\",\n"
+ " \"n_layer\": %d,\n"
+ " \"file_bytes\": %llu,\n"
+ " \"requested_range\": [%d, %d],\n"
+ " \"reported_range\": [%d, %d],\n"
+ " \"mmap\": %s,\n"
+ " \"touched\": %s,\n"
+ " \"use_extra_bufts\": %s,\n"
+ " \"has_token_embeddings\": %s,\n"
+ " \"has_output_head\": %s,\n"
+ " \"tied_output_head\": %s,\n"
+ " \"mapped_bytes\": %llu,\n"
+ " \"resident_bytes\": %llu,\n"
+ " \"registered_tensors\": %d,\n"
+ " \"registered_bytes\": %llu,\n"
+ " \"unexpected_registered_tensors\": [],\n"
+ " \"missing_owned_layers\": [],\n"
+ " \"vm_size_bytes\": %llu,\n"
+ " \"vm_rss_bytes\": %llu,\n"
+ " \"vm_hwm_bytes\": %llu\n"
+ "}\n",
+ json_escape(model_path).c_str(),
+ json_escape(arch).c_str(),
+ n_layer,
+ (unsigned long long) bytes_on_disk,
+ start, end,
+ report.start_layer, report.end_layer,
+ use_mmap ? "true" : "false",
+ touch ? "true" : "false",
+ use_extra_bufts ? "true" : "false",
+ report.has_token_embeddings ? "true" : "false",
+ report.has_output_head ? "true" : "false",
+ tied_tail ? "true" : "false",
+ (unsigned long long) report.mapped_bytes,
+ (unsigned long long) report.resident_bytes,
+ (int) tensors.size(),
+ (unsigned long long) registered_bytes,
+ (unsigned long long) proc.vm_size,
+ (unsigned long long) proc.vm_rss,
+ (unsigned long long) proc.vm_hwm);
+
+ llama_model_free(model);
+ llama_backend_free();
+ return 0;
+}

1
packages/node/native/llama/patches/SHA256SUMS
View File

@@ -4,3 +4,4 @@
4871a37544df658980a01b4f94151a90b609fb144c931b4a814309ee608ebb46 0003-owned-range-filtered-state-report.patch
19d451ce259150ffede793c4eb547425375c0fcd97caf326b43e8f1a204f05b6 0004-dense-boundary-io-endpoint-guard.patch
cf263357a6a8de193f710836c7c467c38cac7099975303ee2628e0609daf5a47 0005-worker-range-report-hook.patch
23b4b8c56243d52ba682f0034022a86bf8ded007885be5b659cf5158ff3eb429 0006-meshnet-range-report-tool.patch

24
packages/node/native/llama/patches/UPSTREAM-ASSUMPTIONS.json
View File

@@ -112,6 +112,30 @@
"llama_internal_get_tensor_map(const llama_model *) in src/llama-model.h",
"gguf empty-context writer API: gguf_init_empty, gguf_add_tensor, gguf_write_to_file"
]
},
"0006-meshnet-range-report-tool.patch": {
"concern": "range-reporting",
"files": {
"CMakeLists.txt": {
"before": "a9afcffa68bed7cbd8fad39ad9f95ad784251234",
"after": "868793b826f565df7f041e7ba55820b5ad744b10"
},
"tools/meshnet-range-report/CMakeLists.txt": {
"before": null,
"after": "24401007ee85e217c2741a42c7119fad323ff08a"
},
"tools/meshnet-range-report/meshnet-range-report.cpp": {
"before": null,
"after": "49a5eb2a05bf6514e166453ea0e35b8bc9c5fdf6"
}
},
"api_assumptions": [
"llama_model_params carries meshnet_owned_layer_start/end, use_mmap, and use_extra_bufts",
"llama_model_meshnet_range_report C API and llama_meshnet_range_report fields (patch 0005)",
"llama_internal_get_tensor_map(const llama_model *) in src/llama-model.h",
"llama_model_meta_val_str and llama_model_n_layer public accessors",
"top-level CMakeLists add_subdirectory of a project-owned tool directory after the llama target"
]
}
}
}

1
packages/node/native/llama/patches/series
View File

@@ -3,3 +3,4 @@
0003-owned-range-filtered-state-report.patch
0004-dense-boundary-io-endpoint-guard.patch
0005-worker-range-report-hook.patch
0006-meshnet-range-report-tool.patch