MCPcopy Create free account

hub / github.com/antirez/llama.cpp-deepseek-v4-flash / functions

Functions13,473 in github.com/antirez/llama.cpp-deepseek-v4-flash

⨍ Functions 13,473◇ Types & classes 3,460↳ Endpoints 3
↓ 16 callersFunctionpack_q8_0_quants
ggml/src/ggml-hexagon/ggml-hexagon.cpp:701
↓ 16 callersFunctionread
tests/test-json-schema-to-grammar.cpp:74
↓ 16 callersFunctionrecv_msg
ggml/src/ggml-rpc/ggml-rpc.cpp:268
↓ 16 callersFunctionregex_to_reversed_partial_regex
Transforms a regex pattern to a partial match pattern that operates on a reversed input string to find partial final matches of the original pattern.
common/regex-partial.cpp:71
↓ 16 callersMethodset_swa_pattern
src/llama-hparams.cpp:8
↓ 16 callersMethodstream
* @brief Get or create a stream for a given index. * @param stream Index of the stream. * @return The stream corresponding to the given inde
ggml/src/ggml-cann/common.h:612
↓ 16 callersMethodtensor_force_quant
(self, name: str, new_name: str, bid: int | None, n_dims: int)
convert_hf_to_gguf.py:581
↓ 16 callersFunctionvaddvq_f32
ggml/src/ggml-cpu/ggml-cpu-impl.h:122
↓ 16 callersFunctionvpaddq_s32
ggml/src/ggml-cpu/ggml-cpu-impl.h:112
↓ 15 callersFunctionXXH3_mix16B
* DISCLAIMER: There are known *seed-dependent* multicollisions here due to * multiplication by zero, affecting hashes of lengths 17 to 240. * * How
examples/gguf-hash/deps/xxhash/xxhash.h:4656
↓ 15 callersFunction_print
(text="", end="\n")
scripts/server-test-parallel-tc.py:45
↓ 15 callersFunctionaclnn_cast
* @brief Casts the data type of a source tensor to a destination tensor. * * This function casts the data type of the source tensor `acl_src` to the
ggml/src/ggml-cann/aclnn_ops.cpp:187
↓ 15 callersMethodallocated_total
tests/test-alloc.cpp:24
↓ 15 callersFunctionclamp
ggml/src/ggml-sycl/element_wise.cpp:298
↓ 15 callersMethoddecode
tests/test-backend-sampler.cpp:116
↓ 15 callersMethodget_ne
ggml/src/gguf.cpp:179
↓ 15 callersMethodget_type
(val: Any)
gguf-py/gguf/constants.py:4204
↓ 15 callersFunctionggml_backend_buffer_get_type
ggml/src/ggml-backend.cpp:193
↓ 15 callersFunctionggml_backend_get_default_buffer_type
ggml/src/ggml-backend.cpp:237
↓ 15 callersFunctionggml_backend_load_best
ggml/src/ggml-backend-reg.cpp:461
↓ 15 callersFunctionggml_backend_synchronize
ggml/src/ggml-backend.cpp:414
↓ 15 callersFunctionggml_can_repeat
check if t1 can be represented as a repetition of t0
ggml/src/ggml.c:1555
↓ 15 callersFunctionggml_conv_2d_direct
ggml/src/ggml.c:4774
↓ 15 callersFunctionggml_div
ggml/src/ggml.c:2273
↓ 15 callersFunctionggml_metal_op_concurrency_reset
ggml/src/ggml-metal/ggml-metal-ops.cpp:147
↓ 15 callersFunctionggml_new_graph_custom
ggml/src/ggml.c:7261
↓ 15 callersFunctionggml_relu
ggml/src/ggml.c:2703
↓ 15 callersFunctionggml_soft_max
ggml/src/ggml.c:4038
↓ 15 callersFunctionggml_tanh
ggml/src/ggml.c:2675
↓ 15 callersFunctiongguf_get_tensor_name
ggml/src/gguf.cpp:1048
↓ 15 callersFunctiongguf_init_empty
ggml/src/gguf.cpp:367
↓ 15 callersFunctionhvx_vec_reduce_sum_f32x2
ggml/src/ggml-hexagon/htp/hvx-reduce.h:64
↓ 15 callersMethodid_to_title
(string)
gguf-py/gguf/metadata.py:235
↓ 15 callersFunctionincr_ptr_aligned
ggml/src/ggml.c:7228
↓ 15 callersMethodis_empty
src/llama-kv-cells.h:72
↓ 15 callersFunctionllama_perf_context_print
src/llama-context.cpp:3511
↓ 15 callersFunctionllama_set_param
src/llama-context.cpp:2702
↓ 15 callersFunctionllama_vocab_get_add_eos
src/llama-vocab.cpp:3931
↓ 15 callersFunctionmake_context
tests/test-alloc.cpp:125
↓ 15 callersMethodparse
common/peg-parser.cpp:899
↓ 15 callersMethodrelease
tools/server/server-context.cpp:410
↓ 15 callersFunctionrun
tests/test-alloc.cpp:586
↓ 15 callersMethodto_json
tools/server/server-task.cpp:30
↓ 15 callersMethodunset_option
common/preset.cpp:138
↓ 15 callersFunctionusage
tools/quantize/quantize.cpp:125
↓ 15 callersFunctionverify_parsing
tests/test-grammar-parser.cpp:25
↓ 14 callersFunctionXXH3_avalanche
* This is a fast avalanche stage, * suitable when input bits are already partially mixed */
examples/gguf-hash/deps/xxhash/xxhash.h:4507
↓ 14 callersFunctionXXH64_round
! @copydoc XXH32_round */
examples/gguf-hash/deps/xxhash/xxhash.h:3401
↓ 14 callersMethod_get
( self, offset: int, dtype: npt.DTypeLike, count: int = 1, override_order: None | Literal['I', 'S', '<
gguf-py/gguf/gguf_reader.py:197
↓ 14 callersFunction_print
(text="", end="\n")
scripts/server-test-structured.py:41
↓ 14 callersMethodadd
ggml/src/ggml-rpc/ggml-rpc.cpp:224
↓ 14 callersMethodadd_add_space_prefix
(self, value: bool)
gguf-py/gguf/gguf_writer.py:1096
↓ 14 callersMethodadd_expert_count
(self, count: int)
gguf-py/gguf/gguf_writer.py:826
↓ 14 callersFunctionapir_decode_size_t
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:273
↓ 14 callersFunctionapir_encode
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:143
↓ 14 callersFunctionapir_encode_size_t
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:268
↓ 14 callersFunctionassign_names
tests/test-alloc.cpp:147
↓ 14 callersMethodbuildFinalTimings
( capturedTimings: ChatMessageTimings | undefined, agenticTimings: ChatMessageAgenticTimings )
tools/server/webui/src/lib/stores/agentic.svelte.ts:588
↓ 14 callersFunctionbuild_tool_call
Helper to build tool call JSON
tests/test-chat-auto-parser.cpp:782
↓ 14 callersMethoddecode
(self, ids: list[int])
tests/test-tokenizer-random.py:124
↓ 14 callersFunctiondummy_backend_init
tests/test-alloc.cpp:93
↓ 14 callersMethodget_n_rs
src/llama-memory-recurrent.cpp:1137
↓ 14 callersMethodget_rope_freq_base
src/llama-model.cpp:8569
↓ 14 callersMethodget_rope_freq_scale
src/llama-model.cpp:8573
↓ 14 callersFunctionggml_backend_buffer_name
ggml/src/ggml-backend.cpp:103
↓ 14 callersFunctionggml_backend_buft_is_host
ggml/src/ggml-backend.cpp:72
↓ 14 callersFunctionggml_backend_sched_get_tensor_backend
ggml/src/ggml-backend.cpp:1969
↓ 14 callersFunctionggml_backend_tensor_get_async
ggml/src/ggml-backend.cpp:268
↓ 14 callersFunctionggml_cl2_init
Initialize device if it is supported (returns nullptr if it is not).
ggml/src/ggml-opencl/ggml-opencl.cpp:3087
↓ 14 callersFunctionggml_gallocr_hash_get
ggml/src/ggml-alloc.c:583
↓ 14 callersFunctionggml_repeat
ggml/src/ggml.c:2536
↓ 14 callersFunctionggml_vk_align_size
ggml/src/ggml-vulkan/ggml-vulkan.cpp:6703
↓ 14 callersFunctionggml_vk_ctx_end
ggml/src/ggml-vulkan/ggml-vulkan.cpp:6641
↓ 14 callersFunctionggml_vk_print_matrix_area
ggml/src/ggml-vulkan/ggml-vulkan.cpp:11963
↓ 14 callersFunctionggml_vk_submit
ggml/src/ggml-vulkan/ggml-vulkan.cpp:2410
↓ 14 callersFunctiongguf_check_reserved_keys
ggml/src/gguf.cpp:1072
↓ 14 callersFunctiongguf_find_tensor
ggml/src/gguf.cpp:1027
↓ 14 callersFunctiongguf_get_tensor_offset
ggml/src/gguf.cpp:1043
↓ 14 callersFunctionllama_log_set
src/llama-impl.cpp:32
↓ 14 callersFunctionllama_max_devices
src/llama.cpp:57
↓ 14 callersMethodload
(model_plus: ModelPlus)
examples/convert_legacy_llama.py:331
↓ 14 callersMethodmake_stream_request
( self, method: str, path: str, data: dict | None = None, headers: dic
tools/server/tests/utils.py:349
↓ 14 callersFunctionmove_cursor
common/console.cpp:666
↓ 14 callersFunctionnormalizeModelName
(modelName: string)
tools/server/webui/src/lib/utils/model-names.ts:20
↓ 14 callersMethodreset
tools/server/server-context.cpp:195
↓ 14 callersFunctionsend_msg
ggml/src/ggml-rpc/ggml-rpc.cpp:261
↓ 14 callersFunctiontest_grammar
tests/test-grammar-integration.cpp:188
↓ 14 callersFunctionto_uppercase
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:199
↓ 14 callersFunctionvcvtnq_s32_f32
ggml/src/ggml-cpu/ggml-cpu-impl.h:132
↓ 14 callersFunctionvk_op_unary_push_constants_init
ggml/src/ggml-vulkan/ggml-vulkan.cpp:1150
↓ 13 callersMethod_pack
(self, fmt: str, value: Any, skip_pack_prefix: bool = False)
gguf-py/gguf/gguf_writer.py:1304
↓ 13 callersFunction_print
(text="", end="\n")
scripts/server-test-function-call.py:33
↓ 13 callersMethodadd_description
(self, description: str)
gguf-py/gguf/gguf_writer.py:568
↓ 13 callersMethodadd_expert_shared_count
(self, count: int)
gguf-py/gguf/gguf_writer.py:832
↓ 13 callersFunctioncheck_all_allocated
tests/test-alloc.cpp:187
↓ 13 callersFunctionclip_image_f32_init
tools/mtmd/clip.cpp:2763
↓ 13 callersFunctioncommon_chat_template_direct_apply_impl
common/chat.cpp:756
↓ 13 callersFunctioncommon_sampler_init
common/sampling.cpp:187
↓ 13 callersMethodcreate
* Creates a default GgufMetadataReader instance */
examples/llama.android/lib/src/main/java/com/arm/aichat/gguf/GgufMetadataReader.kt:55
↓ 13 callersFunctionfn
(_m, input, output)
examples/model-conversion/scripts/utils/common.py:104
← previousnext →601–700 of 13,473, ranked by callers