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
↓ 101 callersFunctionmadd
ggml/src/ggml-cpu/llamafile/sgemm.cpp:134
↓ 101 callersMethodspace
Matches zero or more whitespace characters (space, tab, newline). S -> [ \t\n]
common/peg-parser.h:422
↓ 99 callersFunctionggml_are_same_shape
ggml/src/ggml.c:1530
↓ 99 callersMethodrule
common/peg-parser.cpp:1230
↓ 98 callersFunctionget_pointer
ggml/src/ggml-sycl/common.hpp:609
↓ 96 callersMethodappend
src/llama-vocab.cpp:525
↓ 95 callersFunctionhsum
ggml/src/ggml-cpu/llamafile/sgemm.cpp:232
↓ 93 callersFunctionggml_backend_tensor_set
ggml/src/ggml-backend.cpp:324
↓ 93 callersFunctionggml_view_2d
ggml/src/ggml.c:3706
↓ 93 callersMethodresize
src/llama-kv-cells.h:63
↓ 90 callersFunctionmerge_maps
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:403
↓ 86 callersFunctioncommon_tokenize
common/common.cpp:1571
↓ 86 callersFunctiontoken
token() encodes a 32-bit ID as 5 bytes: a 0xff marker followed by the ID in big-endian order.
tests/test-grammar-integration.cpp:45
↓ 82 callersMethodinsert
common/peg-parser.cpp:131
↓ 81 callersMethodas_string
common/jinja/value.h:134
↓ 81 callersFunctionggml_concat
ggml/src/ggml.c:2588
↓ 81 callersFunctionggml_new_tensor_4d
ggml/src/ggml.c:1844
↓ 80 callersFunctionggml_is_quantized
ggml/src/ggml.c:1337
↓ 80 callersFunctionggml_new_tensor_2d
ggml/src/ggml.c:1825
↓ 79 callersMethoderror
()
tools/server/webui/src/lib/stores/mcp.svelte.ts:296
↓ 77 callersMethodstrip
common/jinja/string.cpp:163
↓ 76 callersFunctionggml_get_next_tensor
ggml/src/ggml.c:1958
↓ 76 callersFunctionggml_webgpu_make_tensor_bind_group_entry
ggml/src/ggml-webgpu/ggml-webgpu.cpp:460
↓ 76 callersFunctionggml_webgpu_tensor_misalignment
ggml/src/ggml-webgpu/ggml-webgpu.cpp:387
↓ 75 callersFunctionggml_get_first_tensor
ggml/src/ggml.c:1942
↓ 75 callersFunctionggml_set_param
ggml/src/ggml.c:7781
↓ 75 callersFunctionggml_view_4d
ggml/src/ggml.c:3748
↓ 74 callersMethoddump
common/peg-parser.cpp:938
↓ 73 callersFunctionggml_op_name
ggml/src/ggml.c:1343
↓ 73 callersFunctionllama_decode
src/llama-context.cpp:3484
↓ 73 callersMethodstream
ggml/src/ggml-sycl/common.hpp:328
↓ 72 callersFunctionggml_webgpu_hash_combine
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp:55
↓ 72 callersFunctionmul_sum_i8_pairs_acc_int32x8
Integer variant of the function defined in ggml-quants.c multiply int8_t, add results pairwise twice and return as 256 bit int vector, then add the ac
ggml/src/ggml-cpu/arch/x86/repack.cpp:165
↓ 71 callersFunctionggml_free
ggml/src/ggml.c:1629
↓ 71 callersFunctionggml_get_op_params_f32
ggml/src/ggml-impl.h:158
↓ 70 callersMethodadd_kv
src/llama-model-saver.cpp:52
↓ 70 callersFunctiondp4a
ggml/src/ggml-sycl/dpct/helper.hpp:1851
↓ 70 callersFunctionggml_set_input
ggml/src/ggml.c:7773
↓ 69 callersFunctioncommon_token_to_piece
common/common.cpp:1603
↓ 69 callersMethodmap
common/chat-peg-parser.cpp:252
↓ 67 callersFunctionggml_init
ggml/src/ggml.c:1577
↓ 67 callersFunctionhas_capability_or_fail
ggml/src/ggml-sycl/dpct/helper.hpp:2020
↓ 67 callersFunctionlog
common/console.cpp:1146
↓ 67 callersMethodread
ggml/src/gguf.cpp:258
↓ 66 callersMethodempty
ggml/src/ggml-hexagon/ggml-hexagon.cpp:1598
↓ 66 callersFunctionggml_cann_type_mapping
ggml/src/ggml-cann/acl_tensor.cpp:28
↓ 64 callersFunctionmul_sum_i8_pairs_acc_int32x16
multiply int8_t, add results pairwise twice and return as 512 bit int vector，then add the accumulator
ggml/src/ggml-cpu/arch/x86/repack.cpp:134
↓ 64 callersMethodn_tokens
tools/server/server-task.cpp:1982
↓ 64 callersMethodnode
ggml/src/ggml-metal/ggml-metal-ops.cpp:75
↓ 63 callersFunctioncommon_batch_add
common/common.cpp:1548
↓ 62 callersMethodclear
tools/server/server-common.h:204
↓ 62 callersMethodformat_tensor_name
(self, key: gguf.MODEL_TENSOR, bid: int | None = None, suffix: str = ".weight")
convert_hf_to_gguf.py:523
↓ 62 callersFunctionggml_format_name
ggml/src/ggml.c:1921
↓ 62 callersFunctionllama_model_get_vocab
src/llama-model.cpp:9319
↓ 62 callersMethodtag
Tags create nodes in the generated AST for semantic purposes. Unlike rules, you can tag multiple nodes with the same tag.
common/peg-parser.h:511
↓ 61 callersMethodencode
src/llama-context.cpp:1259
↓ 61 callersFunctionggml_transpose
ggml/src/ggml.c:3828
↓ 61 callersFunctionllama_get_memory
src/llama-context.cpp:3252
↓ 61 callersMethodsize
common/speculative.cpp:156
↓ 61 callersFunctionvaddvq_s32
ggml/src/ggml-cpu/ggml-cpu-impl.h:118
↓ 60 callersMethodadd_string
(self, key: str, val: str)
gguf-py/gguf/gguf_writer.py:316
↓ 60 callersMethodclear
* @brief Clear all graphs from the cache (also frees memory). */
ggml/src/ggml-cann/common.h:414
↓ 60 callersMethodtype
Note: only for debugging and error reporting purposes
common/jinja/value.h:130
↓ 60 callersMethoduntil
Matches all characters until a delimiter is found (delimiter not consumed). S -> (!delim .)
common/peg-parser.h:426
↓ 60 callersMethodwrite
src/llama-context.cpp:2352
↓ 59 callersFunctionggml_is_contiguous_1
ggml/src/ggml.c:1480
↓ 59 callersFunctionggml_vk_tensor_subbuffer
ggml/src/ggml-vulkan/ggml-vulkan.cpp:6527
↓ 59 callersFunctiongguf_free
ggml/src/gguf.cpp:860
↓ 58 callersMethod__init__
(self, *args, **kwargs)
convert_hf_to_gguf.py:10240
↓ 58 callersMethodclear
src/llama-batch.cpp:655
↓ 58 callersFunctiondma_queue_pop
ggml/src/ggml-hexagon/htp/hex-dma.h:216
↓ 58 callersFunctionggml_dup_tensor
ggml/src/ggml.c:1861
↓ 57 callersFunctionQ6_Vsf_equals_Vw
ggml/src/ggml-hexagon/htp/hvx-base.h:181
↓ 57 callersFunctioncalculate_diff_split
common/chat-auto-parser-helpers.cpp:87
↓ 57 callersFunctionggml_tensor_overhead
ggml/src/ggml.c:1444
↓ 56 callersFunctionggml_is_contiguous_rows
ggml/src/ggml.c:1505
↓ 56 callersFunctionsimple_assist_msg
tests/test-chat.cpp:820
↓ 55 callersFunctionnearest_int
===================== Helper functions
ggml/src/ggml-quants.c:559
↓ 54 callersFunctionassert_equals
tests/test-chat.cpp:90
↓ 54 callersMethodexecute
execute with error handling
common/jinja/runtime.cpp:54
↓ 54 callersFunctionllama_sampler_chain_add
src/llama-sampler.cpp:876
↓ 53 callersFunctionfastdiv
ggml/src/ggml-hexagon/htp/hex-fastdiv.h:26
↓ 53 callersMethodhas
* Check if key exists and is not expired.
tools/server/webui/src/lib/utils/cache-ttl.ts:83
↓ 53 callersMethodlog
tools/mtmd/mtmd-helper.cpp:74
↓ 53 callersMethodset
* Set a value in cache with TTL.
tools/server/webui/src/lib/utils/cache-ttl.ts:64
↓ 52 callersFunctionggml_set_op_params_i32
ggml/src/ggml-impl.h:163
↓ 52 callersFunctionggml_vec_dot
ggml/src/ggml-cpu/ggml-cpu-impl.h:509
↓ 52 callersFunctionhvx_vec_splat_f32
ggml/src/ggml-hexagon/htp/hvx-base.h:41
↓ 51 callersMethodadd
common/ngram-mod.cpp:25
↓ 51 callersFunctionggml_backend_tensor_get
ggml/src/ggml-backend.cpp:339
↓ 51 callersFunctionhex_round_up
ggml/src/ggml-hexagon/htp/hex-utils.h:65
↓ 51 callersFunctionllama_batch_free
src/llama-batch.cpp:907
↓ 51 callersFunctionllama_model_free
src/llama-model.cpp:9327
↓ 50 callersMethodoptional
Matches zero or one occurrence of a parser, always succeeds. S -> A?
common/peg-parser.h:395
↓ 49 callersFunctiondma_queue_push
ggml/src/ggml-hexagon/htp/hex-dma.h:271
↓ 49 callersMethodget_input
ggml/src/ggml-openvino/openvino/node_context.h:68
↓ 49 callersMethodload
src/llama-vocab.cpp:1749
↓ 48 callersFunctionXXH_readLE64
examples/gguf-hash/deps/xxhash/xxhash.h:3328
↓ 48 callersFunctioncommon_params_parse
common/arg.cpp:884
↓ 48 callersMethodfail
common/peg-parser.h:140
← previousnext →101–200 of 13,473, ranked by callers