| You passed `inputs_embeds` and `input_ids` to… | validation | error | generate, encoder-decoder, inputs-embeds, api-misuse |
| is an abstract class. Only classes inheriting this class… | exception | error | abstract-class, logits-processor, api-misuse |
| `get_mask_sizes` can only be called on Attention layers… | validation | error | cache, linear-attention, mask, valueerror |
| Invalid `cache_implementation | validation | error | python, transformers, generation, kv-cache, generation-config, validation |
| Invalid padding strategy | exception | error | feature-extractor, padding, config, transformers |
| The `layer_types` entries must be in | exception | error | config, layer-types, validation, deprecated |
| When setting ``truncation=True``, make sure that… | exception | error | feature-extractor, truncation, audio, transformers |
| You called `has_previous_state` on layer index | validation | error | cache, linear-attention, layer-type, valueerror |
| Indexing with integers is not available when using Python… | exception | error | feature-extractor, batchfeature, api-misuse, transformers |
| Unknown fusion type | exception | error | python, transformers, fusion, config-validation |
| only a single or a list of entries is supported but got… | exception | error | feature-extractor, audio, type-error, transformers |
| function not found in ACT2FN mapping | exception | error | deepgemm, bfloat16, moe, dtype |
| You can only update int, float, bool or string values in… | validation | error | config, update-from-string, type-error |
| No server currently running on | validation | error | cli, chat, connection-refused, network, serving |
| A GenerationConfig must be provided or set in the model. | validation | error | generation-config, validation, continuous-batching |
| Input image type not supported | validation | error | image-processing, pil, typeerror, input-validation |
| Sliding window attention layers do not support block table | exception | error | not-implemented, sliding-window, attention, continuous-batching |
| min should be < max (got min: , max: ) | exception | error | deepgemm, dtype, bfloat16, activations |
| `low_memory=True` is not supported after the beam search… | exception | error | |
| mean must have elements if it is an iterable, got | validation | error | image-processing, normalization, validation, valueerror |
| key isn't in the original config dict | validation | error | config, update-from-string, validation |
| `max_new_tokens` must be greater than 0, but is | validation | error | python, transformers, generation, generation-config, validation |
| When setting ``padding= | exception | error | feature-extractor, padding, audio, transformers |
| Type resolution failed for | exception | error | |
| Missing required field | validation | error | config, dataclass, validation |
| std must have elements if it is an iterable, got | validation | error | image-processing, normalization, validation, valueerror |
| size must have 1 or 2 elements if it is a list or tuple | validation | error | image-processing, resize, validation, valueerror |
| `prefix_allowed_tokens_fn` returned an empty list for batch… | validation | error | |
| You should provide exactly one of `layers` or… | validation | error | cache, constructor, validation, valueerror |
| size must have 2 elements representing the height and width… | validation | error | image-processing, crop, validation, valueerror |
| Using a `device_map`, `tp_plan`, `torch.device` context… | validation | error | |
| Got but expected a value in [0, 1] | validation | error | validation, scheduler, configuration, continuous-batching |
| Only `Union[X, NoneType]` (i.e., `Optional[X]`) is allowed… | exception | error | |
| Padding dimensions are negative. Please make sure that the… | exception | error | |
| You provided `compile_config` as an instance of | validation | error | python, transformers, generation, torch-compile, generation-config, type-error |
| Please correct the following DeepSpeed config values that… | validation | error | |
| DeepGEMM Mega MoE requires `hidden_dim` and… | validation | error | |
| `min_length` has to be a non-negative integer, but is | validation | error | validation, logits-processor, types, generation-config |
| Invalid fusion config for | exception | error | python, transformers, fusion, config-validation, type-error |
| Unknown quantization backend | validation | error | cache, quantization, backend, valueerror |
| DeepGEMM Mega MoE requires a `process_group` for the EP… | validation | error | |
| When passing device_map as a string, the value needs to be… | validation | error | |
| scale_fmt='ue8m0' requires torch.float8_e8m0fnu, which is… | exception | error | |
| DeepGEMM's FP4 (int8-packed) path requires a Blackwell… | exception | error | |
| size must have 2 elements | validation | error | image-processing, resize, validation, valueerror |
| Failed to apply weight conversion for | exception | error | |
| Sequence parallelism is enabled but no SP process group is… | exception | error | |
| Padding dimensions are negative. Please make sure that the… | exception | error | |
| The model must use a 'static' caching implementation to be… | exception | error | |
| DeepGEMM Mega MoE requires FP4-packed expert weights… | exception | error | |
| Must have at least `1` token to score after the first… | exception | error | |
| image must be a numpy array | validation | error | image-processing, numpy, normalization, typeerror |
| Got but expected a value >= 1 | validation | error | validation, scheduler, configuration, continuous-batching |
| Each element in `sequence_bias` has to be a non-empty list… | validation | error | |
| Ngrams should be of shape (batch_size, num_ngrams… | validation | error | |
| The model must have a generation config to be exported with… | exception | error | |
| The model must have caching enabled to be exported with… | exception | error | |
| When generating with token healing, you must pass the… | exception | error | |
| Size must contain 'height' and 'width' keys, or… | exception | error | |
| is on the meta device because it was offloaded, but we… | validation | error | |
| Unresolved type detected, which should have been done with… | exception | error | |
| You can't pass device_map as a negative int. If you want to… | validation | error | |
| Require guidance scale >1 to use the classifier free… | validation | error | |
| Got type which is not supported, only `PIL.Image.Image`… | validation | error | |
| cannot use beam search with a cache currently, as the cache… | exception | error | |
| Truthy value expected: got | exception | error | |
| Each key in `sequence_bias` has to be a non-empty tuple of… | validation | error | |
| No hyperparameter search backend available.\n - To install | exception | error | |
| prefix_allowed_tokens_fn is not supported for continuous… | validation | error | |
| Failed to load `kernels-community/deep-gemm` — check that a… | exception | error | |
| DeepGEMM requires block-wise quantized FP8 weights, but the… | validation | error | |
| greenlist_ratio has be in range between 0.0 and 1.0… | validation | error | |
| Each list in `bad_words_ids` has to be a list of positive… | validation | error | |
| You picked the backend, but it is not installed. Run . | exception | error | |
| Unsupported annotation format | validation | error | |
| Ngrams should be of shape (batch_size, num_ngrams… | validation | error | |
| seeding_scheme has to be one of [`selfhash`, `lefthash`]… | validation | error | |
| assistant_model is not supported for continuous batching… | validation | error | |
| `input_starting_length` has to be a non-negative integer… | validation | error | |
| DeepGEMM experts path requires bfloat16 hidden states, got | validation | error | |
| `image_mean` and `image_std` must both be specified if… | validation | error | |
| `sequence_bias` has to be a dict with floats as values, but… | validation | error | |
| Some specified arguments are not used by the… | exception | error | |
| Pad size must contain 'height' and 'width' keys only. Got… | exception | error | |
| `sequence_bias` has to be a dict with tuples as keys, but is | validation | error | |
| ZeRO inference only makes sense with ZeRO Stage 3 - please… | exception | error | |
| `eos_token_id` has to be a list of positive integers, but is | validation | error | |
| DeepGEMM experts dispatch does not support static… | exception | error | |
| DeepGEMM requires `block_size` ∈ | validation | error | |
| The size dictionary must have keys 'height' and 'width'. Got | exception | error | |
| max_cache_len must be provided, either as an argument or in… | exception | error | |
| Input weight should be of type nn.Parameter, got | validation | error | |
| batch_size must be provided, either as an argument or in… | exception | error | |
| This pytree flattening function should only be applied to… | exception | error | |
| Some keys are not used by the HfArgumentParser | exception | error | |
| streaming is not supported for continuous batching. Got | validation | error | |
| DeepGEMM linear requires FP16 or BF16 activations, got | validation | error | |
| `bad_words_ids` has to be a non-empty list, but is | validation | error | |
| `bad_words_ids` has to be a list of lists, but is | validation | error | |
| `size` and `resample` must be specified if `do_resize` is… | validation | error | |