[pull] master from ggml-org:master

.github/workflows/build-apple.yml

@@ -59,6 +59,7 @@ jobs:
           cmake -B build -G Xcode \
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=ON \
+            -DLLAMA_BUILD_APP=OFF \
             -DLLAMA_BUILD_COMMON=OFF \
             -DLLAMA_BUILD_EXAMPLES=OFF \
             -DLLAMA_BUILD_TOOLS=OFF \
@@ -89,6 +90,7 @@ jobs:
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=ON \
             -DLLAMA_OPENSSL=OFF \
+            -DLLAMA_BUILD_APP=OFF \
             -DLLAMA_BUILD_EXAMPLES=OFF \
             -DLLAMA_BUILD_TOOLS=OFF \
             -DLLAMA_BUILD_TESTS=OFF \
@@ -138,6 +140,7 @@ jobs:
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=ON \
             -DLLAMA_BUILD_COMMON=OFF \
+            -DLLAMA_BUILD_APP=OFF \
             -DLLAMA_BUILD_EXAMPLES=OFF \
             -DLLAMA_BUILD_TOOLS=OFF \
             -DLLAMA_BUILD_TESTS=OFF \
@@ -163,6 +166,7 @@ jobs:
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=ON \
             -DLLAMA_BUILD_COMMON=OFF \
+            -DLLAMA_BUILD_APP=OFF \
             -DLLAMA_BUILD_EXAMPLES=OFF \
             -DLLAMA_BUILD_TOOLS=OFF \
             -DLLAMA_BUILD_TESTS=OFF \
@@ -206,6 +210,7 @@ jobs:
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=ON \
             -DLLAMA_OPENSSL=OFF \
+            -DLLAMA_BUILD_APP=OFF \
             -DLLAMA_BUILD_EXAMPLES=OFF \
             -DLLAMA_BUILD_TOOLS=OFF \
             -DLLAMA_BUILD_TESTS=OFF \

.github/workflows/build-cmake-pkg.yml

@@ -19,9 +19,14 @@ jobs:
       - name: Build
         run: |
           PREFIX="$(pwd)"/inst
-          cmake -S . -B build -DCMAKE_PREFIX_PATH="$PREFIX" \
-                -DLLAMA_OPENSSL=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=OFF \
-                -DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_APP=OFF -DCMAKE_BUILD_TYPE=Release
+          cmake -S . -B build \
+                -DCMAKE_PREFIX_PATH="$PREFIX" \
+                -DLLAMA_OPENSSL=OFF \
+                -DLLAMA_BUILD_TESTS=OFF \
+                -DLLAMA_BUILD_TOOLS=OFF \
+                -DLLAMA_BUILD_EXAMPLES=OFF \
+                -DLLAMA_BUILD_APP=OFF \
+                -DCMAKE_BUILD_TYPE=Release
           cmake --build build --config Release
           cmake --install build --prefix "$PREFIX" --config Release
 

.github/workflows/release.yml

@@ -1108,6 +1108,7 @@ jobs:
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=ON \
             -DLLAMA_OPENSSL=OFF \
+            -DLLAMA_BUILD_APP=OFF \
             -DLLAMA_BUILD_EXAMPLES=OFF \
             -DLLAMA_BUILD_TOOLS=OFF \
             -DLLAMA_BUILD_TESTS=OFF \

.pi/gg/SYSTEM.md

@@ -1,7 +1,7 @@
 You are a coding agent. Here are some very important rules that you must follow:
 
 General:
-- By very precise and concise when writing code, comments, explanations, etc.
+- Be very precise and concise when writing code, comments, explanations, etc.
 - PR and commit titles format: `<module> : <title>`. Lookup recents for examples
 - Don't try to build or run the code unless you are explicitly asked to do so
 - Use the `gh` CLI tool when querying PRs, issues, or other GitHub resources
@@ -16,7 +16,8 @@ Pull requests (PRs):
 - New branch names are prefixed with "gg/"
 - Before opening a pull request, ask the user to confirm the description
 - When creating a pull request, look for the repository's PR template and follow it
-- For the AI usage disclosure section, write "YES. llama.cpp + pi"
+- For the AI usage disclosure section, write "YES. llama.cpp + pi + [MODEL]"
+- Ask the user to tell you what model was used and write it in place of [MODEL]
 - Always create the pull requests in draft mode
 
 Commits:

build-xcframework.sh

@@ -7,6 +7,7 @@ VISIONOS_MIN_OS_VERSION=1.0
 TVOS_MIN_OS_VERSION=16.4
 
 BUILD_SHARED_LIBS=OFF
+LLAMA_BUILD_APP=OFF
 LLAMA_BUILD_EXAMPLES=OFF
 LLAMA_BUILD_TOOLS=OFF
 LLAMA_BUILD_TESTS=OFF
@@ -31,6 +32,7 @@ COMMON_CMAKE_ARGS=(
     -DCMAKE_XCODE_ATTRIBUTE_STRIP_INSTALLED_PRODUCT=NO
     -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
     -DBUILD_SHARED_LIBS=${BUILD_SHARED_LIBS}
+    -DLLAMA_BUILD_APP=${LLAMA_BUILD_APP}
     -DLLAMA_BUILD_EXAMPLES=${LLAMA_BUILD_EXAMPLES}
     -DLLAMA_BUILD_TOOLS=${LLAMA_BUILD_TOOLS}
     -DLLAMA_BUILD_TESTS=${LLAMA_BUILD_TESTS}

conversion/base.py

@@ -1617,6 +1617,11 @@ def _set_vocab_hybriddna(self):
         assert max(tokenizer.vocab.values()) < vocab_size  # ty: ignore[unresolved-attribute]
 
         reverse_vocab = {id_: encoded_tok for encoded_tok, id_ in tokenizer.vocab.items()}  # ty: ignore[unresolved-attribute]
+        # k-mers can share text with a base-vocab BPE token (e.g. CCCCCC) and get
+        # dropped by get_vocab(); a reserved marker suffix (U+E000) keeps each
+        # k-mer's own id (llama.cpp strips it on detokenization)
+        for kmer in tokenizer.kmers:  # ty: ignore[unresolved-attribute]
+            reverse_vocab[tokenizer.dna_token_to_id[kmer]] = kmer + "\ue000"  # ty: ignore[unresolved-attribute]
         added_vocab = tokenizer.get_added_vocab()  # ty: ignore[unresolved-attribute]
         added_tokens_decoder = tokenizer.added_tokens_decoder  # ty: ignore[unresolved-attribute]
 

examples/llama.android/lib/build.gradle.kts

@@ -25,6 +25,7 @@ android {
                 arguments += "-DCMAKE_VERBOSE_MAKEFILE=ON"
 
                 arguments += "-DBUILD_SHARED_LIBS=ON"
+                arguments += "-DLLAMA_BUILD_APP=OFF"
                 arguments += "-DLLAMA_BUILD_COMMON=ON"
                 arguments += "-DLLAMA_OPENSSL=OFF"
 

src/llama-vocab.cpp

@@ -1581,6 +1581,11 @@ struct llm_tokenizer_plamo2_session {
     const llm_tokenizer_plamo2 & tokenizer;
 };
 
+// reserved suffix (U+E000) that keeps DNA k-mers distinct from identical
+// base-vocab BPE tokens (e.g. CCCCCC) in token_to_id; erased from id_to_token
+// text at load
+static const std::string dna_kmer_marker = "\xee\x80\x80";
+
 struct llm_tokenizer_hybriddna_session : llm_tokenizer_bpe_session {
     llm_tokenizer_hybriddna_session(const llama_vocab & vocab, const llm_tokenizer_bpe & tokenizer) : llm_tokenizer_bpe_session{vocab, tokenizer}, vocab{vocab} {}
 
@@ -1636,34 +1641,22 @@ struct llm_tokenizer_hybriddna_session : llm_tokenizer_bpe_session {
                 c = char(c - 32);
             }
         }
-        auto is_valid_kmer = [](const std::string & s) {
-            for (char c : s) {
-                if (c != 'A' && c != 'C' && c != 'G' && c != 'T') {
-                    return false;
-                }
-            }
-            return true;
+
+        // k-mers carry the reserved marker suffix; a non-ACGT k-mer simply
+        // isn't in the vocab and falls back to <oov>
+        auto kmer_token = [&](const std::string & kmer) {
+            const auto tok = vocab.text_to_token(kmer + dna_kmer_marker);
+            return tok != LLAMA_TOKEN_NULL ? tok : oov_id;
         };
 
         size_t i = 0;
         for (; i + k <= seq.size(); i += k) {
-            const std::string kmer = seq.substr(i, k);
-            if (is_valid_kmer(kmer)) {
-                const auto tok = vocab.text_to_token(kmer);
-                output.push_back(tok != LLAMA_TOKEN_NULL ? tok : oov_id);
-            } else {
-                output.push_back(oov_id);
-            }
+            output.push_back(kmer_token(seq.substr(i, k)));
         }
         if (i < seq.size()) {
             std::string kmer = seq.substr(i);
             kmer.append(k - kmer.size(), 'A');
-            if (is_valid_kmer(kmer)) {
-                const auto tok = vocab.text_to_token(kmer);
-                output.push_back(tok != LLAMA_TOKEN_NULL ? tok : oov_id);
-            } else {
-                output.push_back(oov_id);
-            }
+            output.push_back(kmer_token(kmer));
         }
     }
 
@@ -2357,6 +2350,23 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
     }
     GGML_ASSERT(id_to_token.size() == token_to_id.size());
 
+    // hybriddna: the marker suffix kept k-mer ids distinct in token_to_id; erase
+    // it from id_to_token so the k-mers detokenize to the bare DNA sequence. The
+    // k-mers are the block right after <oov>, so only scan from there.
+    if (tokenizer_model == "hybriddna") {
+        const auto idx = token_to_id.find("<oov>");
+        if (idx != token_to_id.end()) {
+            auto it = id_to_token.begin() + idx->second + 1;
+            for (; it != id_to_token.end(); ++it) {
+                std::string & text = it->text;
+                if (text.size() > dna_kmer_marker.size()
+                        && text.compare(text.size() - dna_kmer_marker.size(), dna_kmer_marker.size(), dna_kmer_marker) == 0) {
+                    text.erase(text.size() - dna_kmer_marker.size());
+                }
+            }
+        }
+    }
+
     init_tokenizer(type);
 
     // determine the newline token: LLaMA "<0x0A>" == 10 == '\n', Falcon 193 == '\n'

tools/batched-bench/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-batched-bench executable
 
 set(TARGET llama-batched-bench)

tools/cli/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR} ../server)
 target_link_libraries(${TARGET} PUBLIC server-context llama-common ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-cli executable
 
 set(TARGET llama-cli)

tools/completion/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-completion executable
 
 set(TARGET llama-completion)

tools/fit-params/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-fit-params executable
 
 set(TARGET llama-fit-params)

tools/llama-bench/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-bench executable
 
 set(TARGET llama-bench)

tools/perplexity/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-perplexity executable
 
 set(TARGET llama-perplexity)

tools/quantize/CMakeLists.txt

@@ -8,6 +8,10 @@ set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-quantize executable
 
 set(TARGET llama-quantize)

tools/server/CMakeLists.txt

@@ -44,6 +44,10 @@ target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 target_include_directories(${TARGET} PRIVATE ../mtmd ${CMAKE_SOURCE_DIR})
 target_link_libraries(${TARGET} PUBLIC server-context llama-ui cpp-httplib ${CMAKE_THREAD_LIBS_INIT})
 
+if(LLAMA_TOOLS_INSTALL)
+    install(TARGETS ${TARGET} LIBRARY)
+endif()
+
 # llama-server executable
 
 set(TARGET llama-server)