Functions — github.com/ml-explore/mlx-lm

CodeHub MCPcopy Create free account

hub / github.com/ml-explore/mlx-lm / functions

Functions2,622 in github.com/ml-explore/mlx-lm

⨍ Functions 2,622◇ Types & classes 816↳ Endpoints 9

mlx_lm/models/cache.py:804

mlx_lm/models/cache.py:887

mlx_lm/models/cache.py:1123

mlx_lm/models/cache.py:1477

Methodencode_batch

(self, texts, **kwargs)

mlx_lm/tokenizer_utils.py:494

Methodexpand_quant

mlx_lm/models/cache.py:259

mlx_lm/generate.py:1062

In-place extend this cache with the other cache.

mlx_lm/models/cache.py:642

Methodextra_repr

mlx_lm/models/internlm3.py:64

Methodextra_repr

mlx_lm/models/internlm2.py:63

Methodextra_repr

mlx_lm/models/rope_utils.py:110

mlx_lm/models/cache.py:673

mlx_lm/models/cache.py:1080

mlx_lm/models/cache.py:1417

Methodextract_cache

(self, idx: int)

mlx_lm/generate.py:1059

In-place filter to keep just the given indices in the cache.

mlx_lm/models/cache.py:632

In-place filter to keep just the given indices in the cache.

mlx_lm/models/cache.py:850

mlx_lm/tokenizer_utils.py:49

mlx_lm/tokenizer_utils.py:85

mlx_lm/tokenizer_utils.py:150

mlx_lm/tokenizer_utils.py:220

mlx_lm/models/cache.py:681

mlx_lm/models/cache.py:980

mlx_lm/models/cache.py:1285

Methodfind_think_end

(self, tokens, start=None, end=None)

mlx_lm/tokenizer_utils.py:382

Methodfind_think_start

(self, tokens, start=None, end=None)

mlx_lm/tokenizer_utils.py:374

Functionfrequency_penalty_processor

(tokens, logits)

mlx_lm/sample_utils.py:361

Methodfrom_base

( embedding: nn.Embedding, r: int = 8, dropout: float = 0.0, scale: float = 20

mlx_lm/tuner/dora.py:132

Methodfrom_base

( linear: nn.Linear, r: int = 8, dropout: float = 0.0, scale: float = 20.0,

mlx_lm/tuner/lora.py:13

Methodfrom_base

( linear: nn.Module, r: int = 8, dropout: float = 0.0, scale: float = 20.0,

mlx_lm/tuner/lora.py:103

Methodfrom_base

( embedding: nn.Embedding, r: int = 8, dropout: float = 0.0, scale: float = 20

mlx_lm/tuner/lora.py:200

Methodfrom_dict

mlx_lm/models/phixtral.py:27

Methodfrom_dict

mlx_lm/models/base.py:14

Methodfrom_dict

mlx_lm/models/qwen3_5_moe.py:15

Methodfrom_state

(cls, state, meta_state)

mlx_lm/models/cache.py:170

(self, dequantize: bool = False)

mlx_lm/tuner/dora.py:153

(self, dequantize: bool = False)

mlx_lm/tuner/lora.py:34

(self, dequantize: bool = False)

mlx_lm/tuner/lora.py:120

(self, dequantize: bool = False)

mlx_lm/tuner/lora.py:219

(self, dequantize: bool = False)

mlx_lm/models/afm7.py:54

Methodgenerate_until

Generate greedily until a stopping sequence :param requests: list[Instance] A list of Instance objects with property `args` which

mlx_lm/evaluate.py:309

Functionget_current_weather

mlx_lm/examples/openai_tool_use.py:42

Functionget_keys_for_lora

mlx_lm/tuner/utils.py:88

tests/test_server.py:524

Methodget_next_request

mlx_lm/server.py:707

Methodhandle_chat_completions

Handle a chat completion request. Returns: mx.array: A mx.array of the tokenized prompt from the request body

mlx_lm/server.py:1579

Methodhandle_text_completions

Handle a text completion request. Returns: mx.array: A mx.array of the tokenized prompt from the request body

mlx_lm/server.py:1601

Methodhas_newline_token

mlx_lm/gguf.py:87

Methodhas_thinking

mlx_lm/tokenizer_utils.py:391

Methodhas_tool_calling

mlx_lm/tokenizer_utils.py:427

mlx_lm/models/gemma4_text.py:655

Methodinit_quant

mlx_lm/models/cache.py:252

Functioninner_fn

(params, *args, **kwargs)

mlx_lm/tuner/trainer.py:32

Methodinput_dims

mlx_lm/models/afm7.py:105

Methodinput_dims

mlx_lm/models/afm7.py:130

Methodinput_dims

mlx_lm/models/switch_layers.py:64

Methodinput_dims

mlx_lm/models/switch_layers.py:109

Methodis_mpt_layer

mlx_lm/models/glm4_moe_lite.py:382

Methodis_trimmable

tests/test_server.py:87

Methodis_trimmable

mlx_lm/models/cache.py:146

Methodis_trimmable

mlx_lm/models/cache.py:211

Methodis_trimmable

mlx_lm/models/cache.py:306

Methodis_trimmable

mlx_lm/models/cache.py:542

Methodis_trimmable

mlx_lm/models/cache.py:788

Methodis_trimmable

mlx_lm/models/cache.py:1002

Methodis_trimmable

mlx_lm/models/cache.py:1317

mlx_lm/models/kimi_vl.py:85

Methodkeepalive_callback

(processed_tokens, total_tokens)

tests/test_server.py:482

Methodkeepalive_callback

(processed, total)

mlx_lm/server.py:1410

Methodlast_segment

Return the last segment of readable text since last time this property was accessed.

mlx_lm/tokenizer_utils.py:53

mlx_lm/models/telechat3.py:201

mlx_lm/models/qwen2.py:220

mlx_lm/models/ernie4_5.py:164

mlx_lm/models/gpt_oss.py:324

mlx_lm/models/kimi_k25.py:75

mlx_lm/models/phixtral.py:201

mlx_lm/models/cohere2.py:216

mlx_lm/models/qwen3_next.py:446

mlx_lm/models/minimax.py:377

mlx_lm/models/recurrent_gemma.py:434

mlx_lm/models/smollm3.py:66

mlx_lm/models/gemma4_text.py:651

mlx_lm/models/bailing_moe_linear.py:585

mlx_lm/models/lfm2_moe.py:364

mlx_lm/models/qwen3_moe.py:258

mlx_lm/models/openelm.py:219

mlx_lm/models/plamo.py:211

mlx_lm/models/granite.py:192

mlx_lm/models/gpt2.py:199

mlx_lm/models/glm4_moe.py:395

mlx_lm/models/mimo_v2_flash.py:367

mlx_lm/models/gemma.py:174

mlx_lm/models/lfm2-vl.py:47

mlx_lm/models/kimi_linear.py:480

mlx_lm/models/step3p5.py:393

mlx_lm/models/exaone_moe.py:364

mlx_lm/models/minicpm.py:203

mlx_lm/models/afm7.py:389

mlx_lm/models/glm4_moe_lite.py:523

mlx_lm/models/qwen3_5.py:301

← previous next →1,901–2,000 of 2,622, ranked by callers