fix lint

[windreamer]

No description provided.

[Copilot]

Pull request overview

This PR addresses linting issues by reformatting C++ code across multiple files in the turbomind codebase. The changes are purely cosmetic, improving code alignment, breaking long lines, and ensuring consistent formatting without altering any functionality.

Changes:

• Reformatted line breaks and alignment in parameter lists, function calls, and variable declarations
• Aligned inline comments for better readability
• Ensured compliance with line length limits in configuration and kernel files

Reviewed changes

Copilot reviewed 7 out of 9 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
src/turbomind/turbomind.cc	Reformatted long line assignment to fit line length limits
src/turbomind/models/llama/moe_ffn_layer.cc	Aligned function call parameters for invokeMoeGate_V2
src/turbomind/models/llama/llama_params.h	Aligned inline comments for weight type variables
src/turbomind/models/llama/LlamaDecoderLayerWeight.cc	Aligned variable declarations for is_moe_layer and ffn_wtype
src/turbomind/kernels/gemm/moe_utils_v2.cu	Aligned function parameters, kernel parameters, and variable declarations throughout the file
src/turbomind/kernels/attention/codegen/decoding_sm80_576_bf16_u8.cu	Reformatted template instantiations to single lines
src/turbomind/kernels/attention/codegen/decoding_sm80_576_bf16_u4.cu	Reformatted template instantiations to single lines
src/turbomind/kernels/attention/codegen/decoding_sm80_576_bf16_bf16.cu	Reformatted template instantiations with return type on separate line
src/turbomind/kernels/attention/codegen/attention_sm80_576_bf16.cu	Reformatted template instantiation to single line

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.