ErrLookup › huggingface/candle

huggingface/candle

Minimalist ML framework for Rust · Rust · 491 source files

Analyzed at d5fee525bf on 2026-09-02. 254 documented errors.

Code / MessageTypeSeverityTags
unsqueeze: maximum size for tensor at dimension
validation error rust, candle, unsqueeze, broadcast, shape
unexpected len from chunk
validation error candle, tensor-shape, chunk, flux, model-config
Non contiguous rmsnorm is not implemented
exception error metal, rmsnorm, contiguity, gpu
unsupported const-set f8e4m3
exception error metal, gpu, unsupported-dtype, fp8, candle
Temperature must be non-negative, got
validation error rust, candle, validation, sampling-config
mergeable_ranks is not an object
validation error rust, candle, json, tokenizer, schema-validation
Meta SDPA does not support q dims
validation error sdpa, metal, mask, unsupported
unsupported 'value' data-type
exception error onnx, dtype, unsupported-type, model-loading
unexpected shape for img
validation error candle, tensor-shape, rank, flux, latent-packing
not a f32
exception error candle, gguf, type-mismatch
dtype mismatch, expected
validation error metal, dtype-mismatch, scalar, fill, candle
not implemented yet, self.device
error_code error rust, candle, device-transfer, unimplemented
more dilations than expected in conv1d
validation error onnx, conv1d, unsupported-attribute
unexpected shape for txt
validation error candle, tensor-shape, rank, flux, input-validation
seqlens_q has to be contiguous
validation error cuda, tensor-layout, contiguity, flash-attention
index is too large for tensor dimension
validation error rust, pyo3, tensor, index-out-of-bounds
The given quantized dtype
exception error cuda, quantization, moe, unsupported-dtype
backward not supported for non uniform upscaling factors
exception error autograd, tensor, shape-mismatch, rust
quantized tensor has
validation error cuda, quantization, embedding, corrupt-data, size-mismatch
text_embeddings cannot be empty
validation error rust, candle, validation, empty-input
cannot find in metadata
exception error rust, candle, gguf, moe, missing-metadata
gguf: array of elements needs at least bytes, only remaining
exception error candle, gguf, truncated-file, corrupt-file
Metal contiguous to_dtype
exception error metal, gpu, dtype-cast, candle
compile with '--features flash-attn'
panic error rust, candle, feature-flag, flash-attention, panic
unsupported 'to' value
validation error onnx, cast, unsupported-dtype, rust
shape mismatch on : <>
exception error rust, candle, shape-mismatch, tensor
sliding window is not supported
validation error rust, candle, unsupported-feature, model-config
Not enough audio embeddings: need
validation error rust, candle, voxtral, audio, shape-mismatch
mm_prefix_ranges shape must be
exception error cuda, flash-attn, shape-mismatch, tensor-shape
is a dummy type and cannot be constructed
panic error rust, panic, unsupported-dtype, candle
dimension mismatch in permute, tensor
validation error shape, permute, dimension
axis is too large, tensor rank
validation error rust, candle, axis, shape
Expected CPU storage
exception error device, cpu-only, quantization, candle
flash-attn-varlen expects input tensors of rank 3
validation error cuda, flash-attention, tensor-shape, rank-mismatch
The number of encoder hidden states
validation error tensor-shape, model-config, candle
cannot use slice_set when self and src share their storage
validation error aliasing, in-place, scatter, storage
input1 has to be contiguous
exception error cpu, contiguity, custom-op, candle
gguf: value nesting depth exceeds max
validation error candle, gguf, corrupt-file, security
Either scales or sizes should be present
validation error onnx, resize, missing-input
Invalid audio position
exception error rust, candle, voxtral, audio, index-out-of-range
one_hot: index value
exception error tensor, encoding, validation, rust
no cpu support for flash-attn
exception error cpu, flash-attention, unsupported-platform, cuda-only
embed_dim must be divisible by num_heads
validation error rust, candle, voxtral, config, shape-validation
quantized embedding hidden size
validation error cuda, quantization, embedding, shape, block-size
expected some cross-attn
validation error rust, candle, blip, cross-attention, missing-component
mergeable_ranks ' ' is not a u64
validation error rust, candle, json, tokenizer, type-mismatch
Unsupported nearest_mode for resize
validation error onnx, resize, unsupported-feature
Index out of bounds for dimension with size
validation error onnx, scatternd, index-out-of-bounds
Non contiguous layernorm is not implemented
exception error metal, layernorm, contiguity, candle
one_hot: index out of bounds
exception error tensor, encoding, bounds, rust
Image embedding length
validation error rust, candle, qwen3-vl, shape-mismatch, multimodal
multiple value-types in the same array
exception error candle, gguf, serialization, type-mismatch
timestep out of this schedulers bounds
validation error rust, candle, stable-diffusion, scheduler, timestep
empty codebooks
exception error rust, candle, audio, snac, empty-input
unsupported input type
exception error onnx, invalid-model, protobuf, eval
is a dummy type and does not support parsing
panic critical rust, panic, candle, num-traits, parsing, unsupported-dtype
slice-assign: the range for dim
validation error rust, candle, slice-assign, shape-mismatch
cannot find 'value' attr in 'Constant' for
validation error onnx, constant, unsupported-attribute
index is too low for tensor dimension
validation error rust, pyo3, tensor, negative-index
seqlens_k must be a cuda tensor
validation error cuda, device-mismatch, flash-attention, tensor-placement
top_p must be between 0 and 1, got
validation error rust, candle, validation, sampling-config
only TorchAttn is supported
validation error rust, candle, metavoice, unsupported-feature, config
cannot find for op
exception error onnx, eval, missing-value, graph
unsupported dtype for softmax
exception error dtype, softmax, cpu, candle
cannot find tensor info for
exception error gguf, tensor-names, lookup
dilations have to be the same on both axis
validation error onnx, conv2d, dilations
empty cache despite pos > 0
exception error rust, candle, kv-cache, recurrent-gemma, state-management
cannot reshape tensor of
validation error candle, reshape, shape
cannot find output
exception error onnx, graph, missing-output
Expected f32/f16
validation error candle, quantized, matmul, dtype
only / blocks found
validation error rust, candle, beit, transformer, invalid-index
unsupported const-set f64
exception error metal, gpu, unsupported-dtype, f64, candle
internal error, unexpected current position
exception error gguf, internal-invariant, serialization
slice-assign: upper bound is out of range for dim
validation error rust, candle, slice-assign, bounds
image height is not a multiple of patch height
validation error rust, candle, vision, beit, shape-constraint
unrecognized value-type
exception error gguf, parsing, file-format
shape mismatch in rms-norm
validation error rmsnorm, shape-mismatch, tensor-shape
Unsupported coordinate_transformation_mode for resize
validation error onnx, resize, unsupported-feature
alibi is not supported
validation error config, falcon, unsupported-feature, candle
pixel_values require image_grid_thw
validation error rust, candle, qwen3-vl, multimodal, missing-argument
unexpected dim for , got , expected
exception error onnx, shape-mismatch, dimension, eval
shape mismatch in layer-norm src
validation error shape-mismatch, layernorm, validation, candle
unexpected num-channels in GroupNorm
exception error tensor, shape, normalization, rust
only multi_query_attention=true is supported
validation error config, glm4, unsupported-feature
unexpected bool value
exception error candle, gguf, corrupt-file, encoding
slice-assign: empty range for dim
validation error rust, candle, slice-assign, empty-range
in_channel mismatch between input
exception error shape-mismatch, convolution, tensor, rust
paged flash-attn requires page_block_size
validation error cuda, flash-attention, paged-attention, missing-config
gguf: array length exceeds max
exception error candle, gguf, corrupt-file, security, dos-protection
more pads than expected in conv2d
validation error onnx, conv2d, attribute-format
block_table last dimension must be contiguous
validation error cuda, flash-attention, contiguity, paged-attention
cannot use pad_with_same on an empty tensor
validation error rust, candle, padding, empty-tensor
attribute was of type TENSOR, but no tensor was found
exception error rust, candle, onnx, attribute
only f32 can be quantized
exception error cuda, quantization, dtype, f32
slice-assign requires input with the same rank
validation error rust, candle, slice-assign, rank-mismatch
unexpected lhs length
exception error quantization, matmul, shape-mismatch
mm_prefix_ranges last dimension must be contiguous
exception error cuda, flash-attn, contiguity, stride
pad-mode 'reflect' is not supported
validation error rust, candle, mimi, audio, padding, unsupported-feature
alibi_slopes must be a cuda tensor
validation error cuda, flash-attention, device-mismatch, tensor-device
unexpected rank for , got , expected
exception error onnx, shape-mismatch, eval, input-validation