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
↓ 3 callersMethodgetHealthCheckState
(serverId: string)
tools/server/webui/src/lib/stores/mcp.svelte.ts:350
↓ 3 callersMethodgetModelModalities
* Get modalities for a specific model * Returns cached modalities from model props
tools/server/webui/src/lib/stores/models.svelte.ts:134
↓ 3 callersMethodgetModelProps
* Get props for a specific model (from cache)
tools/server/webui/src/lib/stores/models.svelte.ts:183
↓ 3 callersFunctiongetRequestBody
( input: RequestInfo | URL, init?: RequestInit )
tools/server/webui/src/lib/utils/request-helpers.ts:40
↓ 3 callersMethodgetServerLabel
(server: MCPServerSettingsEntry)
tools/server/webui/src/lib/stores/mcp.svelte.ts:387
↓ 3 callersMethodgetSyncableParameterKeys
* Get all syncable parameter keys. * * @returns Array of parameter keys that can be synced from server
tools/server/webui/src/lib/services/parameter-sync.service.ts:414
↓ 3 callersMethodget_add_space_prefix
src/llama-vocab.cpp:3725
↓ 3 callersFunctionget_alibi_slope
ggml/src/ggml-sycl/common.hpp:689
↓ 3 callersMethodget_alignment
ggml/src/ggml-rpc/ggml-rpc.cpp:949
↓ 3 callersMethodget_alloc_size
ggml/src/ggml-rpc/ggml-rpc.cpp:888
↓ 3 callersMethodget_arch
src/llama-model-loader.cpp:826
↓ 3 callersMethodget_backend
tools/llama-bench/llama-bench.cpp:1481
↓ 3 callersFunctionget_cache_directory
common/hf-cache.cpp:38
↓ 3 callersFunctionget_cache_file_path
tests/gguf-model-data.cpp:567
↓ 3 callersMethodget_data_by_range
Get raw byte data from a remote file by range. If size is not specified, it will read the entire file.
gguf-py/gguf/utility.py:221
↓ 3 callersFunctionget_device_backend_and_type
ggml/src/ggml-sycl/dpct/helper.hpp:78
↓ 3 callersMethodget_dsv4_index_k
src/llama-memory-hybrid-iswa.cpp:801
↓ 3 callersMethodget_env
common/arg.cpp:226
↓ 3 callersFunctionget_field_data
(reader: gguf.GGUFReader, key: str)
gguf-py/gguf/scripts/gguf_new_metadata.py:30
↓ 3 callersFunctionget_file_host_endian
(reader: GGUFReader)
gguf-py/gguf/scripts/gguf_dump.py:21
↓ 3 callersMethodget_global_mem_size
ggml/src/ggml-sycl/dpct/helper.hpp:667
↓ 3 callersFunctionget_img_url
(id: str)
tools/server/tests/unit/test_vision_api.py:8
↓ 3 callersFunctionget_inp_pos_tensor
ggml/src/ggml-openvino/utils.cpp:859
↓ 3 callersMethodget_input_ggml_tensor
ggml/src/ggml-openvino/ggml-decoder.h:125
↓ 3 callersMethodget_k_idxs
src/llama-graph.h:343
↓ 3 callersMethodget_kq_mask_swa
src/llama-graph.h:380
↓ 3 callersFunctionget_logits
tests/test-llama-archs.cpp:285
↓ 3 callersMethodget_max_size
ggml/src/ggml-rpc/ggml-rpc.cpp:961
↓ 3 callersMethodget_mem_attn
src/llama-memory-hybrid.cpp:193
↓ 3 callersMethodget_mem_attn
src/llama-memory-hybrid-iswa.cpp:768
↓ 3 callersMethodget_mem_recr
src/llama-memory-hybrid.cpp:197
↓ 3 callersMethodget_mem_recr
src/llama-memory-hybrid-iswa.cpp:772
↓ 3 callersFunctionget_model_or_exit
tests/get-model.cpp:7
↓ 3 callersMethodget_n
common/ngram-mod.cpp:46
↓ 3 callersMethodget_n_stream
src/llama-kv-cache.cpp:1106
↓ 3 callersFunctionget_pointer_attribute
ggml/src/ggml-sycl/dpct/helper.hpp:1115
↓ 3 callersMethodget_pre_type
src/llama-vocab.cpp:3547
↓ 3 callersFunctionget_primitive_grammar
Returns the needed GBNF primitive grammar for a given GBNF grammar string. Args: grammar (str): The string containing the GBNF gramm
examples/pydantic_models_to_grammar.py:609
↓ 3 callersFunctionget_random_gguf_context
tests/test-gguf.cpp:835
↓ 3 callersFunctionget_repo_path
common/hf-cache.cpp:87
↓ 3 callersMethodget_rows
Helper method that gets table rows for some list of properties. Rows are created by combining those where all provided properties are
scripts/compare-llama-bench.py:312
↓ 3 callersFunctionget_short_name
(long_quant_name)
ggml/src/ggml-cuda/template-instances/generate_cu_files.py:57
↓ 3 callersFunctionget_tensor_size_bytes
(tensor_meta: dict)
examples/model-conversion/scripts/utils/inspect-org-model.py:77
↓ 3 callersMethodget_tensors
(self)
convert_hf_to_gguf.py:519
↓ 3 callersMethodget_type
src/llama-vocab.cpp:2791
↓ 3 callersMethodget_type_and_name
(self, key: str, try_suffixes: Sequence[str] = ())
gguf-py/gguf/tensor_mapping.py:2179
↓ 3 callersMethodget_weight
src/llama-adapter.cpp:138
↓ 3 callersFunctionget_weight_map
(model_path: Path)
examples/model-conversion/scripts/utils/inspect-org-model.py:28
↓ 3 callersFunctionggml_add1_impl
ggml/src/ggml.c:2110
↓ 3 callersFunctionggml_add_impl
ggml/src/ggml.c:2024
↓ 3 callersFunctionggml_are_same_stride
ggml/src/ggml.c:1540
↓ 3 callersFunctionggml_backend_buffer_get_usage
ggml/src/ggml-backend.cpp:188
↓ 3 callersFunctionggml_backend_buffer_is_sycl
ggml/src/ggml-sycl/ggml-sycl.cpp:381
↓ 3 callersFunctionggml_backend_cann_buffer_type
* @brief Retrieves the CANN buffer type for a specified device. * * This function initializes and returns the buffer type interface associated * wi
ggml/src/ggml-cann/ggml-cann.cpp:1600
↓ 3 callersFunctionggml_backend_cpu_init
ggml/src/ggml-cpu/ggml-cpu.cpp:217
↓ 3 callersFunctionggml_backend_event_free
ggml/src/ggml-backend.cpp:531
↓ 3 callersFunctionggml_backend_is_cann
ggml/src/ggml-cann/ggml-cann.cpp:2997
↓ 3 callersFunctionggml_backend_metal_buffer_type_alloc_buffer
common method for allocating shread or private Metal buffers
ggml/src/ggml-metal/ggml-metal.cpp:199
↓ 3 callersFunctionggml_backend_metal_buffer_type_get_alloc_size
ggml/src/ggml-metal/ggml-metal.cpp:210
↓ 3 callersFunctionggml_backend_metal_guid
ggml/src/ggml-metal/ggml-metal.cpp:584
↓ 3 callersFunctionggml_backend_sched_backend_from_buffer
ggml/src/ggml-backend.cpp:845
↓ 3 callersFunctionggml_backend_sched_backend_id
returns the priority of the backend, lower id is higher priority
ggml/src/ggml-backend.cpp:836
↓ 3 callersFunctionggml_backend_sched_backend_id_from_cur
returns the backend that should be used for the node based on the current locations
ggml/src/ggml-backend.cpp:878
↓ 3 callersFunctionggml_backend_sched_get_backend
ggml/src/ggml-backend.cpp:1938
↓ 3 callersFunctionggml_backend_supports_buft
ggml/src/ggml-backend.cpp:460
↓ 3 callersFunctionggml_backend_sycl_graph_compute_impl
ggml/src/ggml-sycl/ggml-sycl.cpp:4541
↓ 3 callersFunctionggml_backend_tensor_alloc
ggml/src/ggml-backend.cpp:1992
↓ 3 callersFunctionggml_backend_tensor_get_2d
ggml/src/ggml-backend.cpp:376
↓ 3 callersFunctionggml_backend_tensor_set_2d
ggml/src/ggml-backend.cpp:354
↓ 3 callersFunctionggml_backend_vk_get_default_buffer_type
ggml/src/ggml-vulkan/ggml-vulkan.cpp:13808
↓ 3 callersFunctionggml_backend_vk_host_buffer_type
Should be changed to return device-specific host buffer type but that probably requires changes in llama.cpp
ggml/src/ggml-vulkan/ggml-vulkan.cpp:13768
↓ 3 callersFunctionggml_backend_webgpu_wait_queue
ggml/src/ggml-webgpu/ggml-webgpu.cpp:500
↓ 3 callersFunctionggml_calc_pool_output_size
ggml/src/ggml.c:4892
↓ 3 callersFunctionggml_can_mul_mat
ggml/src/ggml.c:3237
↓ 3 callersFunctionggml_cann_dup
ggml/src/ggml-cann/aclnn_ops.cpp:854
↓ 3 callersFunctionggml_compute_forward_dup
ggml/src/ggml-cpu/ops.cpp:526
↓ 3 callersFunctionggml_count_equal
ggml/src/ggml.c:2519
↓ 3 callersFunctionggml_cpu_has_sme
ggml/src/ggml-cpu/ggml-cpu.c:3715
↓ 3 callersFunctionggml_cpu_has_sve
ggml/src/ggml-cpu/ggml-cpu.c:3691
↓ 3 callersFunctionggml_diag
ggml/src/ggml.c:3924
↓ 3 callersFunctionggml_dsv4_fp8_kv_quantize
ggml/src/ggml.c:6329
↓ 3 callersFunctionggml_dup_tensor_layout
creates a copy of the tensor with the same memory layout
ggml/src/ggml-backend.cpp:738
↓ 3 callersFunctionggml_dyn_tallocr_remove_block
ggml/src/ggml-alloc.c:151
↓ 3 callersFunctionggml_flash_attn_ext_add_sinks
ggml/src/ggml.c:5387
↓ 3 callersFunctionggml_flash_attn_ext_set_prec
ggml/src/ggml.c:5368
↓ 3 callersFunctionggml_fp16_to_fp32_row
ggml/src/ggml.c:463
↓ 3 callersFunctionggml_fp32_to_fp16
ggml/src/ggml.c:448
↓ 3 callersFunctionggml_gallocr_init_tensor
ggml/src/ggml-alloc.c:969
↓ 3 callersFunctionggml_gallocr_new
ggml/src/ggml-alloc.c:533
↓ 3 callersFunctionggml_gated_delta_net
ggml/src/ggml.c:6177
↓ 3 callersFunctionggml_geglu_split
ggml/src/ggml.c:3006
↓ 3 callersFunctionggml_gelu_f32
ggml/src/ggml-cpu/vec.h:986
↓ 3 callersFunctionggml_gelu_quick_f32
ggml/src/ggml-cpu/vec.h:1035
↓ 3 callersFunctionggml_gemm_q4_0_8x8_q8_0_generic
ggml/src/ggml-cpu/repack.cpp:1768
↓ 3 callersFunctionggml_gemv_q4_0_8x8_q8_0_generic
ggml/src/ggml-cpu/repack.cpp:843
↓ 3 callersFunctionggml_get_f32_1d
ggml/src/ggml-cpu/ggml-cpu.c:1016
↓ 3 callersFunctionggml_get_no_alloc
ggml/src/ggml.c:1645
↓ 3 callersFunctionggml_get_to_fp16_nc_sycl
ggml/src/ggml-sycl/convert.cpp:779
↓ 3 callersFunctionggml_get_to_fp32_sycl
ggml/src/ggml-sycl/convert.cpp:687
↓ 3 callersFunctionggml_glu_split
ggml/src/ggml.c:2963
← previousnext →2,101–2,200 of 13,473, ranked by callers