MCPcopy Create free account

hub / github.com/antirez/llama.cpp-deepseek-v4-flash / types & classes

Types & classes3,460 in github.com/antirez/llama.cpp-deepseek-v4-flash

⨍ Functions 13,473◇ Types & classes 3,460↳ Endpoints 3
↓ 516 callersClassstring
common/jinja/string.h:24
↓ 319 callersClasscommon_arg
common/arg.h:19
↓ 62 callersEnumtype
common/jinja/lexer.h:14
↓ 55 callersClasscommon_peg_parse_result
common/peg-parser.h:86
↓ 52 callersClasspeg_tester
tests/test-chat.cpp:1301
↓ 34 callersClasscommon_peg_parse_context
common/peg-parser.h:167
↓ 30 callersClassraised_exception
common/jinja/runtime.h:579
↓ 24 callersClasstest
tools/llama-bench/llama-bench.cpp:1381
↓ 18 callersClassBuiltinRule
examples/json_schema_to_grammar.py:192
↓ 15 callersClassop_desc
ggml/src/ggml-hexagon/op-desc.h:11
↓ 13 callersClassLoraTorchTensor
convert_lora_to_gguf.py:41
↓ 13 callersClassTensor
convert_llama_ggml_to_gguf.py:101
↓ 13 callersClassutf8_parse_result
common/unicode.h:10
↓ 12 callersClassServerProcess
tools/server/tests/utils.py:45
↓ 12 callersClasscommon_chat_peg_mapper
common/chat-peg-parser.h:10
↓ 12 callersEnumllm_kv
src/llama-model-saver.cpp:52
↓ 12 callersClasssub_sat
ggml/src/ggml-sycl/dpct/helper.hpp:1862
↓ 11 callersEnumllm_kv
src/llama-model-loader.cpp:292
↓ 10 callersEnumgguf_type
tests/test-gguf.cpp:133
↓ 9 callersClassMetadataDetails
gguf-py/gguf/scripts/gguf_new_metadata.py:23
↓ 9 callersClasscommon_params_fit_exception
common/fit.cpp:25
↓ 9 callersClasshasher
Note: this is a simple hasher, not cryptographically secure, just for hash table usage
common/jinja/utils.h:52
↓ 9 callersClassnot_implemented_exception
common/jinja/value.h:185
↓ 8 callersClassLLM_KV
src/llama-arch.h:595
↓ 8 callersClassLazyTensor
examples/convert_legacy_llama.py:432
↓ 8 callersClassUnquantizedTensor
examples/convert_legacy_llama.py:385
↓ 8 callersEnumggml_backend_meta_split_axis
ggml/src/ggml-backend-meta.cpp:26
↓ 7 callersClassGGUFReader
gguf-py/gguf/gguf_reader.py:111
↓ 7 callersClasscommon_speculative_config
common/speculative.cpp:43
↓ 6 callersClassSiglipVisionConfig
r""" This is the configuration class to store the configuration of a [`SiglipVisionModel`]. It is used to instantiate a Siglip vision encoder
tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py:39
↓ 6 callersClasslexer_exception
common/jinja/lexer.h:152
↓ 5 callersClassGGUFWriter
gguf-py/gguf/gguf_writer.py:65
↓ 5 callersClassReaderField
gguf-py/gguf/gguf_reader.py:39
↓ 5 callersClassSiglipVisionTransformer
tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py:388
↓ 5 callersEnumllama_pooling_type
tools/server/server-context.h:26
↓ 5 callersEnumllm_kv
src/llama-arch.h:144
↓ 5 callersClasstest_operation_info
tests/test-backend-ops.cpp:633
↓ 4 callersClassGGUFValue
gguf-py/gguf/gguf_writer.py:50
↓ 4 callersClassLazyStorageKind
examples/convert_legacy_llama.py:566
↓ 4 callersClassModelPlus
examples/convert_legacy_llama.py:462
↓ 4 callersClassParams
examples/convert_legacy_llama.py:164
↓ 4 callersClassUnquantizedDataType
examples/convert_legacy_llama.py:71
↓ 4 callersEnumllama_vocab_type
tools/server/server-context.h:46
↓ 4 callersEnumllama_vocab_type
include/llama.h:72
↓ 4 callersClassserver_task
tools/server/server-task.h:129
↓ 4 callersClassserver_tokens
* server_tokens is a helper to manage the input tokens and image for the server. * it is made this way to simplify the logic of KV cache management.
tools/server/server-common.h:128
↓ 3 callersClassLLM_TN
src/llama-arch.h:637
↓ 3 callersClassMessage
examples/llama.android/app/src/main/java/com/example/llama/MessageAdapter.kt:9
↓ 3 callersClassTokenType
gguf-py/gguf/constants.py:4064
↓ 3 callersClassToolDefinition
tools/server/tests/unit/test_tool_call.py:43
↓ 3 callersClassToolFunction
tools/server/tests/unit/test_tool_call.py:38
↓ 3 callersClassToolParameters
tools/server/tests/unit/test_tool_call.py:33
↓ 3 callersClassanalyze_tools
common/chat-auto-parser.h:296
↓ 3 callersClassbackend_init_info
tests/test-backend-ops.cpp:734
↓ 3 callersClassllama_adapter_lora_weight
src/llama-adapter.h:48
↓ 3 callersEnumllama_pooling_type
examples/embedding/embedding.cpp:38
↓ 3 callersClassllama_tensor_weight
src/llama-model-loader.h:33
↓ 3 callersClassparser_exception
common/jinja/parser.h:16
↓ 3 callersClasssegment
common/chat-auto-parser.h:425
↓ 3 callersClassstat
ggml/src/ggml-cpu/ggml-cpu.c:631
↓ 2 callersClassCodeEditor
scripts/jinja/jinja-tester.py:171
↓ 2 callersClassGgufMetadataReaderImpl
* Utility class to read GGUF model files and extract metadata key-value pairs. * This parser reads the header and metadata of a GGUF v3 file (little-
examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:17
↓ 2 callersClassJobResult
scripts/snapdragon/qdc/run_qdc_jobs.py:69
↓ 2 callersClassLLM_TN_IMPL
helper to handle gguf constants usage: const auto tn = LLM_TN(LLM_ARCH_LLAMA); std::string name = tn(LLM_TENSOR_OUTPUT); -> "out
src/llama-arch.h:613
↓ 2 callersClassLlamaBenchDataCSV
scripts/compare-llama-bench.py:530
↓ 2 callersClassLlamaBenchDataJSON
scripts/compare-llama-bench.py:492
↓ 2 callersClassLogReader
tools/server/tests/unit/test_kv_keep_only_active.py:8
↓ 2 callersClassOutputFile
examples/convert_legacy_llama.py:769
↓ 2 callersClassPartialLoraTensor
convert_lora_to_gguf.py:35
↓ 2 callersClassTrieNode
examples/json_schema_to_grammar.py:281
↓ 2 callersClassbase64_error
common/base64.hpp:36
↓ 2 callersClasscommon_schema_info
Probes a JSON schema to extract information about its structure and type constraints.
common/json-schema-to-grammar.h:15
↓ 2 callersEnumggml_type
tests/test-gguf.cpp:108
↓ 2 callersEnumgguf_type
ggml/src/gguf.cpp:126
↓ 2 callersClassrethrown_exception
Used to rethrow exceptions with modified messages
common/jinja/runtime.h:588
↓ 2 callersClasssigaction
tools/cli/cli.cpp:376
↓ 2 callersClasssigaction
tools/server/server.cpp:302
↓ 2 callersClasssignal
common/jinja/runtime.h:198
↓ 2 callersClassstat
tools/rpc/rpc-server.cpp:93
↓ 2 callersClassstat
common/common.cpp:903
↓ 2 callersClasstest_summary_info
tests/test-backend-ops.cpp:713
↓ 2 callersClassvalue_equivalence
common/jinja/value.h:195
↓ 1 callersClassAddMetadataDialog
gguf-py/gguf/scripts/gguf_editor_gui.py:755
↓ 1 callersClassArrayEditorDialog
gguf-py/gguf/scripts/gguf_editor_gui.py:340
↓ 1 callersClassAssistantMessageViewHolder
examples/llama.android/app/src/main/java/com/example/llama/MessageAdapter.kt:50
↓ 1 callersClassBook
Represents an entry about a book.
examples/pydantic_models_to_grammar_examples.py:155
↓ 1 callersClassDocsGenerator
scripts/create_ops_docs.py:13
↓ 1 callersClassGGMLFType
convert_llama_ggml_to_gguf.py:27
↓ 1 callersClassGGMLModel
convert_llama_ggml_to_gguf.py:134
↓ 1 callersClassGGMLQuantizationType
gguf-py/gguf/constants.py:4088
↓ 1 callersClassGGMLQuants
gguf-py/tests/test_quants.py:40
↓ 1 callersClassGGMLToGGUF
convert_llama_ggml_to_gguf.py:203
↓ 1 callersClassGGUFEditorWindow
gguf-py/gguf/scripts/gguf_editor_gui.py:814
↓ 1 callersClassGGUFValueType
gguf-py/gguf/constants.py:4188
↓ 1 callersClassGgufMetadata
* Structured metadata of GGUF */
examples/llama.android/lib/src/main/java/com/arm/aichat/gguf/GgufMetadata.kt:9
↓ 1 callersClassHuggingFaceModel
scripts/fetch_server_test_models.py:23
↓ 1 callersClassHyperparameters
convert_llama_ggml_to_gguf.py:47
↓ 1 callersClassInferenceEngineImpl
* JNI wrapper for the llama.cpp library providing Android-friendly access to large language models. * * This class implements a singleton pattern fo
examples/llama.android/lib/src/main/java/com/arm/aichat/internal/InferenceEngineImpl.kt:46
↓ 1 callersClassInvalidFileFormatException
examples/llama.android/lib/src/main/java/com/arm/aichat/gguf/GgufMetadataReader.kt:77
↓ 1 callersClassJinjaTester
scripts/jinja/jinja-tester.py:289
next →1–100 of 3,460, ranked by callers