MCPcopy Create free account

hub / github.com/FoundationVision/LlamaGen / functions

Functions465 in github.com/FoundationVision/LlamaGen

⨍ Functions 465◇ Types & classes 88
↓ 137 callersFunctionprint
(*args, **kwargs)
utils/distributed.py:13
↓ 40 callersMethodload
(cls, path: str, arr_name: str)
evaluations/c2i/evaluator.py:511
↓ 22 callersMethodupdate
(self, input_pos, k_val, v_val)
autoregressive/models/gpt.py:177
↓ 11 callersMethodencode
(self, x)
tokenizer/vqgan/model.py:69
↓ 9 callersMethoddecode_code
(self, code_b, shape, channel_first=True)
tokenizer/vqgan/model.py:80
↓ 9 callersMethodfrom_pretrained
(cls, name="vgg_lpips")
tokenizer/tokenizer_image/lpips.py:75
↓ 8 callersMethod__init__
(self, in_features, hidden_features, out_features)
autoregressive/models/gpt.py:119
↓ 8 callersFunctioncreate_logger
Create a logger that writes to a log file and stdout.
utils/logger.py:4
↓ 7 callersMethod__init__
(self, config: ModelArgs)
tokenizer/tokenizer_image/vq_model.py:29
↓ 7 callersFunctionbuild_dataset
(args, **kwargs)
dataset/build.py:8
↓ 6 callersFunctioncenter_crop_arr
Center cropping implementation from ADM. https://github.com/openai/guided-diffusion/blob/8fb3ad9197f16bbc40620447b2742e13458d2831/guided_diff
dataset/augmentation.py:8
↓ 6 callersMethoddecode
(self, quant)
tokenizer/vqgan/model.py:75
↓ 6 callersFunctioninit_distributed_mode
(args)
utils/distributed.py:20
↓ 6 callersMethodstep
Performs one decoding iteration and returns newly generated results. .. figure:: https://i.imgur.com/sv2HssD.png :alt: Overview o
autoregressive/serve/llm_engine.py:511
↓ 5 callersFunctionNormalize
(in_channels)
tokenizer/vqgan/layer.py:13
↓ 5 callersFunctionNormalize
(in_channels, norm_type='group')
tokenizer/tokenizer_image/vq_model.py:359
↓ 5 callersMethod__init__
(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks, attn_resolutions, dropout=0.0, resam
tokenizer/vqgan/layer.py:176
↓ 5 callersMethod__init__
(self, config: ModelArgs)
autoregressive/serve/gpt_model.py:128
↓ 5 callersMethodempty
(cls)
autoregressive/serve/model_runner.py:56
↓ 5 callersFunctionleaky_relu
(p=0.2)
tokenizer/tokenizer_image/discriminator.py:250
↓ 5 callersFunctionleaky_relu
(p=0.2)
tokenizer/tokenizer_image/discriminator_stylegan.py:96
↓ 5 callersFunctionnonlinearity
(x)
tokenizer/vqgan/layer.py:8
↓ 5 callersMethodsample
( self, logits: torch.Tensor, sampling_metadata: SamplingMetadata, )
autoregressive/serve/gpt_model.py:302
↓ 4 callersMethod__init__
(self)
tokenizer/tokenizer_image/discriminator.py:239
↓ 4 callersFunctionapply_rotary_emb_bs
(x: torch.Tensor, freqs_cis: torch.Tensor)
autoregressive/serve/gpt_model.py:373
↓ 4 callersMethoddummy_data
(self)
dataset/t2i.py:88
↓ 4 callersFunctiongenerate
(model, cond, max_new_tokens, emb_masks=None, cfg_scale=1.0, cfg_interval=-1, **sampling_kwargs)
autoregressive/models/generate.py:127
↓ 4 callersFunctionnonlinearity
(x)
tokenizer/tokenizer_image/vq_model.py:354
↓ 4 callersFunctionupdate_ema
Step the EMA model towards the current model.
utils/ema.py:5
↓ 3 callersMethod__init__
(self, use_dropout=True)
tokenizer/tokenizer_image/lpips.py:55
↓ 3 callersMethodencode
(self, x)
tokenizer/tokenizer_image/vq_model.py:41
↓ 3 callersMethodget_text_embeddings
(self, texts)
language/t5.py:58
↓ 3 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), logging=True)
tokenizer/vqgan/model.py:55
↓ 2 callersMethod__init__
(self)
tokenizer/tokenizer_image/discriminator_stylegan.py:85
↓ 2 callersFunction_batch_pairwise_distances
Compute pairwise distances between two batches of feature vectors.
evaluations/c2i/evaluator.py:426
↓ 2 callersFunction_beam_search_sample
( selected_seq_groups: List[Tuple[List[int], SamplingParams]], is_prompts: List[bool], seq_data: D
autoregressive/serve/sampler.py:325
↓ 2 callersFunction_download_inception_model
()
evaluations/c2i/evaluator.py:585
↓ 2 callersFunction_get_bin_counts_and_mask
( tokens: torch.Tensor, vocab_size: int, num_seqs: int, )
autoregressive/serve/sampler.py:143
↓ 2 callersFunction_get_graph_batch_size
Returns the padded batch size given actual batch size. Batch sizes are 1, 2, 4, _BATCH_SIZE_ALIGNMENT, 2*_BATCH_SIZE_ALIGNMENT, 3*_BATCH_SIZE
autoregressive/serve/model_runner.py:1202
↓ 2 callersMethod_get_stats
Get Stats to be Logged to Prometheus.
autoregressive/serve/llm_engine.py:588
↓ 2 callersFunction_greedy_sample
( selected_seq_groups: List[Tuple[List[int], SamplingParams]], samples: torch.Tensor, )
autoregressive/serve/sampler.py:279
↓ 2 callersFunction_maybe_pynccl
()
autoregressive/serve/model_runner.py:1193
↓ 2 callersFunction_random_sample
( selected_seq_groups: List[Tuple[List[int], SamplingParams]], is_prompts: List[bool], random_samp
autoregressive/serve/sampler.py:298
↓ 2 callersFunctionadopt_weight
(weight, global_step, threshold=0, value=0.)
tokenizer/tokenizer_image/vq_loss.py:43
↓ 2 callersFunctionapply_rotary_emb
(x: torch.Tensor, freqs_cis: torch.Tensor)
autoregressive/models/gpt.py:420
↓ 2 callersMethodcapture
( self, input_ids: torch.Tensor, positions: torch.Tensor, kv_caches: List[torc
autoregressive/serve/model_runner.py:1112
↓ 2 callersMethodclean_caption
(self, caption)
language/t5.py:96
↓ 2 callersMethodcompute_activations
Compute image features for downstream evals. :param batches: a iterator over NHWC numpy arrays in [0, 255]. :return: a tuple
evaluations/c2i/evaluator.py:154
↓ 2 callersFunctioncreat_optimizer
(model, weight_decay, learning_rate, betas, logger)
autoregressive/train/train_c2i.py:28
↓ 2 callersMethoddecode
(self, quant)
tokenizer/tokenizer_image/vq_model.py:47
↓ 2 callersMethoddecode_code
(self, code_b, shape=None, channel_first=True)
tokenizer/tokenizer_image/vq_model.py:52
↓ 2 callersMethodevaluate_pr
Evaluate precision and recall efficiently. :param features_1: [N1 x D] feature vectors for reference batch. :param radii_1:
evaluations/c2i/evaluator.py:337
↓ 2 callersFunctionfind_multiple
(n: int, k: int)
autoregressive/models/gpt.py:18
↓ 2 callersMethodfrechet_distance
Compute the Frechet distance between two sets of statistics.
evaluations/c2i/evaluator.py:84
↓ 2 callersMethodgenerate
Generates the completions for the input prompts. NOTE: This class automatically batches the given prompts, considering the memory con
autoregressive/serve/llm.py:138
↓ 2 callersFunctionget_ckpt_path
(name, root, check=False)
tokenizer/tokenizer_image/lpips.py:42
↓ 2 callersMethodinit_device
(self)
autoregressive/serve/worker.py:89
↓ 2 callersMethodinitialize
(self, input)
tokenizer/tokenizer_image/discriminator.py:91
↓ 2 callersMethodinitialize
(self, input)
tokenizer/tokenizer_image/discriminator_patchgan.py:82
↓ 2 callersMethodmanifold_radii
(self, features: np.ndarray)
evaluations/c2i/evaluator.py:260
↓ 2 callersFunctionmd5_hash
(path)
tokenizer/tokenizer_image/lpips.py:36
↓ 2 callersFunctionnormalize_tensor
(x,eps=1e-10)
tokenizer/tokenizer_image/lpips.py:158
↓ 2 callersMethodpairwise_distances
Evaluate pairwise distances between two batches of feature vectors.
evaluations/c2i/evaluator.py:405
↓ 2 callersFunctionprecompute_freqs_cis_2d
(grid_size: int, n_elem: int, base: int = 10000, cls_token_num=120)
autoregressive/models/gpt.py:404
↓ 2 callersMethodread_activations
(self, npz_path: str)
evaluations/c2i/evaluator.py:150
↓ 2 callersMethodread_statistics
( self, npz_path: str, activations: Tuple[np.ndarray, np.ndarray] )
evaluations/c2i/evaluator.py:176
↓ 2 callersFunctionrequires_grad
Set requires_grad flag for all parameters in a model.
utils/ema.py:17
↓ 2 callersFunctionsample
(logits, temperature: float=1.0, top_k: int=0, top_p: float=1.0, sample_logits=True)
autoregressive/models/generate.py:57
↓ 2 callersMethodset_active_loras
(self, lora_requests: Set[LoRARequest], lora_mapping: LoRAMapping)
autoregressive/serve/model_runner.py:960
↓ 2 callersFunctiontop_k_top_p_filtering
Filter a distribution of logits using top-k and/or nucleus (top-p) filtering Args: logits: logits distribution shape (batch size, vocabula
autoregressive/models/generate.py:16
↓ 1 callersMethod__init__
(self, n_e, e_dim, beta)
tokenizer/vqgan/quantize.py:25
↓ 1 callersMethod__init__
(self, num_features, logdet=False, affine=True, allow_reverse_init=False)
tokenizer/tokenizer_image/discriminator_patchgan.py:71
↓ 1 callersMethod_add_request
( self, prompt: Optional[str], sampling_params: SamplingParams, prompt_token_i
autoregressive/serve/llm.py:221
↓ 1 callersFunction_apply_min_p
Adapted from https://github.com/oobabooga/text-generation-webui/blob/3146124ec01f02c8fb1650a6517cf1b60b537aaf/modules/sampler_hijack.py#L16C1
autoregressive/serve/sampler.py:262
↓ 1 callersFunction_apply_min_tokens_penalty
( logits: torch.Tensor, sampling_metadata: SamplingMetadata, )
autoregressive/serve/sampler.py:160
↓ 1 callersFunction_apply_penalties
(logits: torch.Tensor, prompt_tokens_tensor: torch.Tensor, output_tokens_tensor: torch.Te
autoregressive/serve/sampler.py:207
↓ 1 callersFunction_apply_top_k_top_p
( logits: torch.Tensor, p: torch.Tensor, k: torch.Tensor, )
autoregressive/serve/sampler.py:230
↓ 1 callersFunction_build_sampler_output
Construct Python objects with the output of sampling. Args: on_device_tensors: Tuple containing on-device tensors with the pr
autoregressive/serve/sampler.py:826
↓ 1 callersFunction_check_if_gpu_supports_dtype
(torch_dtype: torch.dtype)
autoregressive/serve/worker.py:322
↓ 1 callersFunction_create_feature_graph
(input_batch)
evaluations/c2i/evaluator.py:598
↓ 1 callersFunction_create_softmax_graph
(input_batch)
evaluations/c2i/evaluator.py:615
↓ 1 callersFunction_get_logprobs
( logprobs: torch.Tensor, sampling_metadata: SamplingMetadata, sample_results: List[Tuple[List[int
autoregressive/serve/sampler.py:637
↓ 1 callersFunction_get_ranks
This function calculates the ranks of the chosen tokens in a logprob tensor. Args: x (torch.Tensor): 2D logprob tensor of shape (N,
autoregressive/serve/sampler.py:618
↓ 1 callersMethod_init_cache_engine
(self)
autoregressive/serve/worker.py:182
↓ 1 callersMethod_init_executor
Initialize the worker and load the model. If speculative decoding is enabled, we instead create the speculative worker.
autoregressive/serve/gpu_executor.py:44
↓ 1 callersMethod_init_non_spec_worker
(self)
autoregressive/serve/gpu_executor.py:55
↓ 1 callersMethod_init_spec_worker
Initialize a SpecDecodeWorker, using a draft model for proposals.
autoregressive/serve/gpu_executor.py:83
↓ 1 callersMethod_init_tokenizer
(self, **tokenizer_init_kwargs)
autoregressive/serve/llm_engine.py:305
↓ 1 callersMethod_initialize_kv_caches
Initialize the KV cache in the worker(s). The workers will determine the number of blocks in both the GPU cache and the swap CPU cach
autoregressive/serve/llm_engine.py:234
↓ 1 callersFunction_load_generation_config_dict
(model_config: ModelConfig)
autoregressive/serve/llm_engine.py:40
↓ 1 callersFunction_modify_greedy_probs_inplace
Modify the probability distributions of the greedily-sampled tokens such that each sampled token has a "probability" of 1.0. This is required by
autoregressive/serve/sampler.py:775
↓ 1 callersFunction_multinomial
( probs: torch.Tensor, num_samples: int, seq_groups: Optional[List[Tuple[List[int], SamplingParams
autoregressive/serve/sampler.py:383
↓ 1 callersMethod_norm
(self, x)
autoregressive/models/gpt.py:143
↓ 1 callersFunction_numpy_partition
(arr, kth, **kwargs)
evaluations/c2i/evaluator.py:648
↓ 1 callersFunction_open_npy_file
(path: str, arr_name: str)
evaluations/c2i/evaluator.py:576
↓ 1 callersMethod_prepare_decode
( self, seq_group_metadata_list: List[SequenceGroupMetadata], )
autoregressive/serve/model_runner.py:448
↓ 1 callersFunction_prepare_fake_inputs
Prepare fake inputs for profile run.
autoregressive/serve/model_runner.py:1217
↓ 1 callersMethod_prepare_prompt
( self, seq_group_metadata_list: List[SequenceGroupMetadata], )
autoregressive/serve/model_runner.py:248
↓ 1 callersMethod_prepare_sample
( self, seq_group_metadata_list: List[SequenceGroupMetadata], prompt_lens: List[int],
autoregressive/serve/model_runner.py:574
↓ 1 callersMethod_process_model_outputs
Apply the model output to the sequences in the scheduled seq groups. Returns RequestOutputs that can be returned to the client.
autoregressive/serve/llm_engine.py:470
next →1–100 of 465, ranked by callers