MCPcopy Create free account

hub / github.com/Luce-Org/lucebox-hub / functions

Functions2,878 in github.com/Luce-Org/lucebox-hub

⨍ Functions 2,878◇ Types & classes 420
↓ 1 callersFunctionmain
()
harness/clients/session_inject_proxy.py:117
↓ 1 callersFunctionmain
()
harness/clients/summarize_backend_pair.py:254
↓ 1 callersFunctionmain
()
harness/clients/llamacpp_compat_proxy.py:482
↓ 1 callersFunctionmain
()
harness/benchmarks/generation_benchmark.py:447
↓ 1 callersFunctionmain
()
server/scripts/convert_dflash_to_gguf.py:388
↓ 1 callersFunctionmain
()
server/scripts/bench_daemon.py:80
↓ 1 callersFunctionmain
()
server/scripts/run.py:87
↓ 1 callersFunctionmain
()
server/scripts/bench_llm.py:270
↓ 1 callersFunctionmain
()
server/scripts/quantize_dflash_draft.py:68
↓ 1 callersFunctionmain
()
server/scripts/quantize_gemma_dflash_q8.py:83
↓ 1 callersFunctionmain
()
server/scripts/quantize_draft_q8.py:116
↓ 1 callersFunctionmain
()
server/scripts/laguna_pflash_niah.py:308
↓ 1 callersFunctionmain
()
server/scripts/bench_agent_loop.py:132
↓ 1 callersFunctionmain
()
server/scripts/parity_laguna.py:118
↓ 1 callersFunctionmain
()
server/scripts/test_server_prefix_cache.py:82
↓ 1 callersFunctionmain
()
server/scripts/tokenize_prompt.py:18
↓ 1 callersFunctionmain
()
server/scripts/phase_split_dual_gpu.py:816
↓ 1 callersFunctionmain
()
server/scripts/test_prefill_cache.py:89
↓ 1 callersFunctionmain
()
server/scripts/bench_agent.py:320
↓ 1 callersFunctionmain
()
server/scripts/bench_he.py:306
↓ 1 callersFunctionmain
()
server/scripts/bench_moe_prefill_streaming.py:113
↓ 1 callersFunctionmain
()
server/scripts/gen_oracle.py:39
↓ 1 callersFunctionmain
()
server/scripts/profile.py:612
↓ 1 callersFunctionmain
()
server/scripts/detokenize.py:7
↓ 1 callersFunctionmain
()
server/scripts/quality_ab_simple.py:169
↓ 1 callersFunctionmain
()
server/scripts/test_multi_turn_prefix_cache.py:88
↓ 1 callersFunctionmain
()
server/scripts/bench_server.py:408
↓ 1 callersFunctionmain
()
server/scripts/quality_humaneval_plus.py:293
↓ 1 callersFunctionmain
()
server/tests/test_server_comprehensive.py:1120
↓ 1 callersFunctionmain
()
server/tests/test_server_smoke.py:309
↓ 1 callersFunctionmain
()
server/tests/test_tokenizer.py:313
↓ 1 callersFunctionmain
()
server/examples/chat.py:85
↓ 1 callersFunctionmake_layer_expert_file_data
server/src/common/moe_expert_compute_ipc.cpp:555
↓ 1 callersFunctionmake_model
Construct the predictor model and move it to device.
scripts/train_predictor.py:340
↓ 1 callersFunctionmake_moe_expert_compute_ipc
server/src/common/moe_expert_compute_ipc.cpp:1123
↓ 1 callersFunctionmake_moe_expert_layers
server/src/common/moe_expert_compute.cpp:112
↓ 1 callersFunctionmake_niah_text
(tokenizer, token_count: int, case_idx: int, needle_fraction: float)
server/scripts/phase_split_dual_gpu.py:448
↓ 1 callersFunctionmake_pflash_env
(args)
server/scripts/phase_split_dual_gpu.py:478
↓ 1 callersFunctionmake_runtime_key
server/src/common/moe_expert_compute.cpp:43
↓ 1 callersFunctionmake_tensor_pattern
server/tests/test_deepseek4_unit.cpp:521
↓ 1 callersFunctionmap_anthropic_messages
(req: dict)
harness/clients/llamacpp_compat_proxy.py:139
↓ 1 callersFunctionmap_name
(name: str)
server/scripts/convert_dflash_to_gguf.py:160
↓ 1 callersFunctionmap_name
(name: str)
server/scripts/quantize_gemma_dflash_q8.py:29
↓ 1 callersFunctionmap_name
(name: str)
server/scripts/quantize_draft_q8.py:54
↓ 1 callersFunctionmap_responses_input
(req: dict)
harness/clients/llamacpp_compat_proxy.py:78
↓ 1 callersFunctionmarker_ok
(text: str)
harness/clients/summarize_backend_pair.py:200
↓ 1 callersMethodmask_token_id
server/src/laguna/laguna_dflash_target.h:76
↓ 1 callersMethodmask_token_id
server/src/gemma4/gemma4_dflash_target.cpp:150
↓ 1 callersMethodmax_context
server/src/qwen35/qwen35_layer_split_adapter.h:56
↓ 1 callersFunctionmessages_for_case
(case: dict[str, Any])
harness/benchmarks/generation_benchmark.py:44
↓ 1 callersFunctionmoe_expert_compute_batch_graph_key
server/src/common/moe_expert_compute_ipc.cpp:285
↓ 1 callersFunctionmoe_expert_compute_batch_max
server/src/common/moe_hybrid_ffn_eval.cpp:53
↓ 1 callersFunctionmoe_expert_compute_drain_exact_fd
server/src/common/moe_expert_compute_ipc.cpp:65
↓ 1 callersFunctionmoe_expert_ipc_input_type_from_env
server/src/common/moe_expert_compute_ipc.cpp:394
↓ 1 callersFunctionmoe_expert_ipc_shared_batch_capacity_from_env
server/src/common/moe_expert_compute_ipc.cpp:384
↓ 1 callersFunctionmoe_expert_placement_fingerprint
server/src/common/moe_expert_compute.cpp:94
↓ 1 callersFunctionmoe_expert_required_shared_bytes
server/src/common/moe_expert_compute_ipc.cpp:455
↓ 1 callersFunctionmoe_expert_shared_bytes_from_env
server/src/common/moe_expert_compute_ipc.cpp:481
↓ 1 callersFunctionmoe_expert_transport_from_env
server/src/common/moe_expert_compute_ipc.cpp:372
↓ 1 callersFunctionnormalize_anthropic_system
(system_text: str | None)
harness/clients/llamacpp_compat_proxy.py:42
↓ 1 callersFunctionnormalize_model_card_stem
server/src/server/model_card.cpp:35
↓ 1 callersFunctionnsys_profile
(cmd: list[str], rep_out: Path)
server/scripts/profile.py:150
↓ 1 callersFunctionobject_matches_tool_schema
server/src/server/tool_parser.cpp:441
↓ 1 callersMethodobserve_selected_tensor
server/src/common/moe_hybrid_routing_stats.cpp:73
↓ 1 callersFunctionopen_expert_mmap
server/src/common/moe_expert_compute_ipc.cpp:494
↓ 1 callersMethodopen_ro
server/src/draft/draft_safetensors_loader.cpp:303
↓ 1 callersMethodopen_ro
server/src/gemma4/gemma4_loader.cpp:48
↓ 1 callersFunctionopenai_chat_text
(body: dict[str, Any] | str)
harness/client_test_runner.py:542
↓ 1 callersFunctionoptimization_flags
(summary: dict)
server/scripts/profile.py:383
↓ 1 callersFunctionoptional_shell_tools
server/test/test_server_unit.cpp:150
↓ 1 callersFunctionpackage_smoke
(work_dir: Path, spec: ClientSpec)
harness/client_test_runner.py:374
↓ 1 callersMethodpark
server/src/common/layer_split_backend.cpp:33
↓ 1 callersMethodpark_draft
(self)
optimizations/pflash/pflash/dflash_client.py:227
↓ 1 callersFunctionparse_ar
(text: str)
server/scripts/profile.py:109
↓ 1 callersFunctionparse_args
()
optimizations/megakernel/final_bench_nvfp4.py:32
↓ 1 callersFunctionparse_args
()
optimizations/megakernel/bench_pp_tg_nvfp4.py:31
↓ 1 callersFunctionparse_args
()
server/scripts/test_server_prefix_cache.py:26
↓ 1 callersFunctionparse_args
()
server/scripts/test_multi_turn_prefix_cache.py:33
↓ 1 callersFunctionparse_backend_device_id
server/src/common/backend_precision.cpp:57
↓ 1 callersFunctionparse_block_tensor_name
server/src/qwen35/gguf_target_loader.cpp:129
↓ 1 callersFunctionparse_block_tensor_name
server/src/laguna/laguna_target_loader.cpp:90
↓ 1 callersFunctionparse_block_tensor_name
server/src/gemma4/gemma4_loader.cpp:135
↓ 1 callersFunctionparse_csv
server/test/bench_laguna_ttft.cpp:34
↓ 1 callersFunctionparse_dflash
(text: str)
server/scripts/profile.py:82
↓ 1 callersFunctionparse_double_list
server/src/server/server_main.cpp:56
↓ 1 callersFunctionparse_drafter_arch
server/src/qwen3/qwen3_drafter.cpp:112
↓ 1 callersFunctionparse_env_overrides
(values: list[str])
server/scripts/phase_split_dual_gpu.py:376
↓ 1 callersFunctionparse_feature_dtype
server/src/common/dflash_feature_ring.cpp:42
↓ 1 callersFunctionparse_function_sig_args
Parse key=value pairs from `<function=name(k="v", k2=123)></function>`. Simplified: we parse key="string" and key=number/bool/null pairs.
server/src/server/tool_parser.cpp:503
↓ 1 callersFunctionparse_llama_calls
(log: str)
harness/clients/summarize_backend_pair.py:66
↓ 1 callersFunctionparse_lucebox_calls
(log: str)
harness/clients/summarize_backend_pair.py:44
↓ 1 callersFunctionparse_placement_backend
server/src/placement/placement_backend.h:24
↓ 1 callersFunctionparse_precision_override
server/src/common/backend_precision.cpp:115
↓ 1 callersFunctionparse_responses_arguments
server/src/server/http_server.cpp:701
↓ 1 callersFunctionparse_single_tool_arg_object
server/src/server/tool_parser.cpp:488
↓ 1 callersFunctionparse_st_header
Tiny hand-rolled parser for the fixed safetensors JSON schema. Safetensors JSON is always a single object: { "name": {"dtype":"BF16","shape":[a,b],"da
server/src/draft/draft_safetensors_loader.cpp:77
↓ 1 callersFunctionpeer_pair_key
server/src/common/peer_access.cpp:35
↓ 1 callersFunctionpflash_register_ggml_kernel
Call this once at init time before running any ggml_flash_attn_sparse graphs.
server/src/pflash_ggml_adapter.cpp:31
↓ 1 callersFunctionphase_name
server/src/server/server_status.h:40
↓ 1 callersFunctionpick_primary_call
(calls: list[dict])
harness/clients/summarize_backend_pair.py:108
← previousnext →1,301–1,400 of 2,878, ranked by callers