🚀 New Features

Model Support

• Added support for Qwen3VL (now using static ViT)

• Enabled Janus model compatibility

• Improved MiniCPM4 model handling

• Enhanced VLM dynamic compilation for ViT models

• Added support for bm1690e platform

• Introduced Lightstereo model support

Core Optimizations

• Implemented ppl-based codegen for bm1690 ops

• Added HdimIsBatch mm pattern cases

• Enhanced auto-round support for LLM models

• Improved AddPostprocess with additional information

• Added same_addr parameter in model_deploy

• CV184x now supports LSTM BF16 operations

New Functionality

• Added new rewriter pattern for optimization

• Implemented dynamic MLIR inference for more ops

• Improved qtable search functions with broader application

• Added manual updates for calibration documentation

• Introduced quant.drawio documentation

⚡ Performance Improvements

• Optimized FAttention with keep_dims attribute

• Enhanced Qwen3VL with static ViT implementation

• Improved dynamic codegen for UpSample and other ops

• Refined shape pattern search for qtable optimization

• Strengthened Rope operation logic

🐛 Critical Fixes

Hardware Specific Fixes

• Fixed BM1688 GELU operation (now uses F32)

• Addressed CV184x GELU BF16 lowering

• Resolved BM1684 conv failure issues

• Fixed Mars3 global depthwise deconv bug

• Corrected CV184x interp input coord (now uses FP32/UINT32)

• Fixed TPUReshapeReorderPattern bug

Model Specific Fixes

• Fixed fattention head slice error

• Addressed multi-deform_attn for broader cases

• Resolved ppl cv184x integration issues

• Fixed cv184x codegen issues

• Corrected bias_correction conv bug

Toolchain Improvements

• Fixed io placement in io_alone mode

• Addressed memory leaks in repeated invoke calls

• Resolved MLIR-693 qtable optimization

• Fixed final qtable bugs

• Corrected tune_num=0 issue in search qtable

• Addressed tpulang no_save mode logging issues

• Fixed inplaceOp liveRange issues

• Resolved dynamic local codegen for ReduceOp

🛠️ Infrastructure Updates

Development Tools

• Added test cases for bm1690e ops and models

• Improved manual documentation

• Enhanced backend support for bm1684x/bm1688

• Removed deprecated 8ch interleave code

• Added shape parameter in set_tensor

• Fixed afterlayergroup pass no_save errors

Documentation

• Updated release records

• Added quant.drawio documentation

• Improved manual updates for calibration

• Fixed various documentation issues