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

↓ 19 callersFunctionggml_aligned_malloc
ggml/src/ggml.c:326
↓ 19 callersFunctionggml_bitset_get
ggml/src/ggml-impl.h:209
↓ 19 callersFunctionggml_cann_set_device
* @brief Set the CANN device to be used. * * @param device The target device ID to set. */
ggml/src/ggml-cann/ggml-cann.cpp:81
↓ 19 callersFunctionggml_is_scalar
ggml/src/ggml.c:1375
↓ 19 callersFunctionggml_set_op_params_f32
ggml/src/ggml-impl.h:168
↓ 19 callersFunctionggml_unary_inplace
ggml/src/ggml.c:5842
↓ 19 callersFunctiongguf_init_from_file
ggml/src/gguf.cpp:847
↓ 19 callersFunctionk
(raw_key: str, arch: str)
tools/mtmd/legacy-models/convert_image_encoder_to_gguf.py:15
↓ 19 callersFunctionllama_sampler_sample
src/llama-sampler.cpp:806
↓ 19 callersFunctionmakeAssistant
(overrides: Partial<DatabaseMessage> = {})
tools/server/webui/tests/unit/agentic-sections.test.ts:7
↓ 19 callersMethodn_embd_v_gqa
src/llama-hparams.cpp:109
↓ 19 callersMethodok
tools/server/server-context.cpp:3171
↓ 19 callersFunctionparseClipboardContent
(clipboardText: string)
tools/server/webui/src/lib/utils/clipboard.ts:165
↓ 19 callersMethodsave
common/peg-parser.cpp:2116
↓ 19 callersFunctionstring_strip
common/common.cpp:417
↓ 19 callersMethodtoString
examples/llama.android/lib/src/main/java/com/arm/aichat/gguf/GgufMetadata.kt:45
↓ 19 callersFunctionunicode_cpts_from_utf8
src/unicode.cpp:997
↓ 18 callersMethodadd_key_value
(self, key: str, val: Any, vtype: GGUFValueType, sub_type: GGUFValueType | None = None)
gguf-py/gguf/gguf_writer.py:277
↓ 18 callersMethodadd_tensor
src/llama-model-saver.cpp:130
↓ 18 callersMethodadd_vision_use_gelu
(self, value: bool)
gguf-py/gguf/gguf_writer.py:1205
↓ 18 callersMethodas_float
common/jinja/value.h:133
↓ 18 callersFunctioncalc_block_size
ggml/src/ggml-hexagon/htp/binary-ops.c:73
↓ 18 callersFunctioncommon_sampler_accept
common/sampling.cpp:434
↓ 18 callersFunctiondigit_range
(from_char: str, to_char: str)
examples/json_schema_to_grammar.py:31
↓ 18 callersFunctionformatMessageForClipboard
( content: string, extras?: DatabaseMessageExtra[], asPlainText: boolean = false )
tools/server/webui/src/lib/utils/clipboard.ts:103
↓ 18 callersFunctionget_device_info
ggml/src/ggml-sycl/dpct/helper.hpp:527
↓ 18 callersMethodget_s_l
src/llama-memory-recurrent.cpp:1157
↓ 18 callersFunctionggml_backend_buft_alloc_buffer
ggml/src/ggml-backend.cpp:38
↓ 18 callersFunctionggml_backend_dev_buffer_type
ggml/src/ggml-backend.cpp:604
↓ 18 callersFunctionggml_glu_impl
ggml/src/ggml.c:2872
↓ 18 callersFunctionggml_graph_node
ggml/src/ggml.c:7440
↓ 18 callersFunctionggml_op_desc
ggml/src/ggml.c:1359
↓ 18 callersFunctionggml_set_output
ggml/src/ggml.c:7777
↓ 18 callersFunctionggml_vk_preallocate_buffers
ggml/src/ggml-vulkan/ggml-vulkan.cpp:12766
↓ 18 callersFunctionhsum_float_8
horizontally add 8 floats
ggml/src/ggml-cpu/arch/loongarch/quants.c:339
↓ 18 callersMethodis_swa
src/llama-hparams.cpp:216
↓ 18 callersFunctionnum_inputs_check
ggml/src/ggml-openvino/openvino/utils.cpp:36
↓ 18 callersMethodreset
tools/mtmd/mtmd-audio.cpp:752
↓ 18 callersFunctionsafe_json_to_str
tools/server/server-common.cpp:1305
↓ 18 callersMethodsetChatLoading
(convId: string, loading: boolean)
tools/server/webui/src/lib/stores/chat.svelte.ts:76
↓ 18 callersMethodsize
common/sampling.cpp:100
↓ 18 callersFunctionstring_replace_all
common/common.cpp:445
↓ 18 callersMethodtest
tools/llama-bench/llama-bench.cpp:1420
↓ 18 callersFunctionunhalf
ggml/src/ggml-cpu/llamafile/sgemm.cpp:80
↓ 17 callersMethodadd_key_length
(self, length: int)
gguf-py/gguf/gguf_writer.py:766
↓ 17 callersMethodadd_sliding_window
(self, value: int)
gguf-py/gguf/gguf_writer.py:949
↓ 17 callersMethodadd_token_scores
(self, scores: Sequence[float])
gguf-py/gguf/gguf_writer.py:1066
↓ 17 callersMethodadd_value_length
(self, length: int)
gguf-py/gguf/gguf_writer.py:769
↓ 17 callersFunctioncommon_chat_templates_apply
common/chat.cpp:2296
↓ 17 callersFunctioncommon_sampler_sample
common/sampling.cpp:528
↓ 17 callersFunctiondma_queue_flush
ggml/src/ggml-hexagon/htp/hex-dma.c:61
↓ 17 callersFunctiondma_queue_push_vtcm_to_ddr
ggml/src/ggml-hexagon/htp/hex-dma.h:316
↓ 17 callersMethodfindMessageIndex
* Finds the index of a message in active messages
tools/server/webui/src/lib/stores/conversations.svelte.ts:191
↓ 17 callersMethodgetConversationMessages
* Gets all messages for a specific conversation * @param convId - The conversation ID * @returns Array of messages
tools/server/webui/src/lib/stores/conversations.svelte.ts:421
↓ 17 callersMethodget_head
src/llama-memory-recurrent.cpp:1141
↓ 17 callersFunctionget_int_from_int8_aligned
ggml/src/ggml-sycl/vecdotq.hpp:74
↓ 17 callersFunctionggml_aligned_free
ggml/src/ggml.c:382
↓ 17 callersFunctionggml_backend_buft_get_alloc_size
ggml/src/ggml-backend.cpp:61
↓ 17 callersFunctionggml_backend_dev_type
ggml/src/ggml-backend.cpp:583
↓ 17 callersFunctionggml_cont_2d
ggml/src/ggml.c:3547
↓ 17 callersFunctionggml_sycl_op_unary
ggml/src/ggml-sycl/element_wise.cpp:471
↓ 17 callersFunctiongguf_get_arr_data
ggml/src/gguf.cpp:920
↓ 17 callersFunctiongguf_remove_key
ggml/src/gguf.cpp:1063
↓ 17 callersFunctionlasx_madd_h_b
ggml/src/ggml-cpu/arch/loongarch/quants.c:303
↓ 17 callersFunctionllama_context_default_params
src/llama-context.cpp:2920
↓ 17 callersMethodn_embd_k_gqa
src/llama-hparams.cpp:103
↓ 17 callersMethodn_embd_r
src/llama-hparams.cpp:155
↓ 17 callersMethodschema
common/peg-parser.cpp:1226
↓ 17 callersFunctionsend_rpc_cmd
RPC request : | rpc_cmd (1 byte) | request_size (8 bytes) | request_data (request_size bytes) | No response
ggml/src/ggml-rpc/ggml-rpc.cpp:309
↓ 17 callersMethodsize
src/llama-memory-hybrid-iswa.cpp:27
↓ 17 callersFunctionuse_adreno_kernels
The optimized gemm and gemv kernels are used for large matrices without batch. tensor is the quantized weights matrix.
ggml/src/ggml-opencl/ggml-opencl.cpp:4573
↓ 16 callersFunctionGGML_TENSOR_LOCALS
ggml/src/ggml-metal/ggml-metal-ops.cpp:4853
↓ 16 callersMethodadd_rope_freq_base
(self, value: float)
gguf-py/gguf/gguf_writer.py:991
↓ 16 callersMethodassign
The variable is assigned to a device pointer.
ggml/src/ggml-sycl/dpct/helper.hpp:2831
↓ 16 callersFunctioncommon_detokenize
common/common.cpp:1625
↓ 16 callersFunctioncommon_utf8_is_complete
common/unicode.cpp:72
↓ 16 callersFunctiondebug_get_tensor_str
ggml/src/ggml-sycl/common.hpp:637
↓ 16 callersFunctiondump_block_mxfp4
ggml/src/ggml-hexagon/ggml-hexagon.cpp:1004
↓ 16 callersFunctiondump_block_q4_0
ggml/src/ggml-hexagon/ggml-hexagon.cpp:319
↓ 16 callersFunctiondump_block_q8_0
======== Q8x4x2 ====================
ggml/src/ggml-hexagon/ggml-hexagon.cpp:667
↓ 16 callersMethodequal_seqs
src/llama-batch.h:16
↓ 16 callersMethodfind_vparam
(self, keys: Iterable[str], optional: bool = False)
convert_hf_to_gguf.py:2275
↓ 16 callersFunctionforeach_function
common/chat.cpp:726
↓ 16 callersMethodfrom_ast
common/chat-peg-parser.cpp:162
↓ 16 callersMethodget_r_l
src/llama-memory-recurrent.cpp:1153
↓ 16 callersFunctionget_scale_shuffle
ggml/src/ggml-cpu/arch/x86/quants.c:540
↓ 16 callersFunctionggml_backend_graph_compute
ggml/src/ggml-backend.cpp:444
↓ 16 callersFunctionggml_backend_meta_buffer_simple_tensor
ggml/src/ggml-backend-meta.cpp:440
↓ 16 callersFunctionggml_cont_3d
ggml/src/ggml.c:3555
↓ 16 callersFunctionggml_n_dims
ggml/src/ggml.c:1397
↓ 16 callersFunctionggml_sum_rows
ggml/src/ggml.c:2456
↓ 16 callersFunctionggml_vqtbl1q_s8
NOTE: not tested
ggml/src/ggml-cpu/ggml-cpu-impl.h:242
↓ 16 callersFunctionggml_webgpu_tensor_equal
Used to determine if two tensors are the same for in-place operations
ggml/src/ggml-webgpu/ggml-webgpu.cpp:419
↓ 16 callersFunctionhmx_ceil_div
ggml/src/ggml-hexagon/htp/hex-utils.h:43
↓ 16 callersMethodis_processing
tools/server/server-context.cpp:288
↓ 16 callersFunctionlasx_xvrepl128vei_h
ggml/src/ggml-cpu/arch/loongarch/quants.c:310
↓ 16 callersFunctionllama_synchronize
src/llama-context.cpp:3119
↓ 16 callersFunctionout
(line="")
scripts/gen-unicode-data.py:158
↓ 16 callersFunctionpack_mxfp4_quants
ggml/src/ggml-hexagon/ggml-hexagon.cpp:1049
↓ 16 callersFunctionpack_q4_0_quants
ggml/src/ggml-hexagon/ggml-hexagon.cpp:362
← previousnext →501–600 of 13,473, ranked by callers