0.7.7

• #205: add in_channels in image_text_to_text
• #204: switch default num_hidden_layers to 4
• #203: Add option to disable patches for torch in command line validate
• #202: add models DeepseekV3ForCausalLM, Gemma3ForCausalLM, Glm4vMoeForConditionalGeneration
• #201: switch CI to 4.55.4
• #200: fixes patches for 4.55.1+, DynamicCache is no longer registered by default, this code moved to executorch.py in transformers
• #199: delete hidden_size and num_attention_heads modification in a config
• #198: support gpt-oss
• #197: updates CI for torch 2.8
• #196: implements a patch to rewrite a loop in modeling_qwen2_vl.VisionAttention

0.7.6

• #193: validates with 4.53.3
• #189: support for task mask-generation
• #192: add support for Gemma-3, add serialization for HybridCache, changes to support transformers>=4.54

0.7.5

• #186: add parameter --output_names to command line validate to change the output names of the onnx exported model
• #185: remove the use of _seen_tokens in DynamicCache (removed in transformers>4.53),
  updates dummpy inputs for feature-extraction
• #184: implements side-by-side

0.7.4

• #178: add a patch for eager_mask to handle assert len(flat_dynamic_shapes) == num_placeholders - num_lifted_inputs
• #177: changes for the next version of onnx, fixes all_dynamic_shape_from_inputs

0.7.3

• #173: fixes function to_any for BaseModelOutput

0.7.2

• #170: patches LlamaRotaryEmbedding
• #168, #169: introduces patch_diffusers
• #166: improves handling of StaticCache
• #165: support for task text-to-image
• #162: improves graphs rendering for historical data

0.7.1

• #159: supports for models with custom code in huggingface
• #158: fix uses of pretrained version
• #156, #157: add plots and other options to deal with the unpredictable
• #155: better aggregation of historical data
• #151, #153: adds command line agg, class CubeLogsPerformance to produce timeseries
• #152: add a function to compute fully dynamic shapes given any inputs

0.7.0

• #149: supports for StaticCache
• #147: simplified log processing
• #146: patch for IdeficsAttention, IdeficsEmbedding
• #145: patch for _compute_dynamic_ntk_parameters (Phi3RotaryEmbedding)
• #144: support for second inputs with different dimension,
  rename test_helper into validate,
  support interpolate_pos_encoding for VitModel,
  update model builder helpers for this PR
  Use ONNX IR for model builder
• #143: compares intermediate results,

0.6.3

• #140: improves command line find
• #131: support for custom kernels in TorchOnnxEvaluator

0.6.1

• #128: patch for Phi3RotaryEmbedding
• #126: add repeat and warmup to command line validate
• #125: handles sequences in TorchOnnxEvaluator
• #123: add subgraphs to TorchOnnxEvaluator
• #122: add local functions to TorchOnnxEvaluator
• #120: enables TorchOnnxEvaluator in command line python -m onnx_diagnostic validate ...
• #115, #116, #117, #118, #119, #127: first steps for TorchOnnxEvaluator
• #114: extends the list of known rewritings
• #113: fixes a couple of issues with ModelBuilder