C++ API Reference#
This section provides documentation for the TensorRT Edge-LLM C++ API.
- Builder Module
- Common Module
- Kernels Module
- Nv Fp4 Mo E Contiguous GEMM Runner
- Nv Fp4 Mo Efc2 Finalize Runner
- Nv Fp4 Mo E Utils
- Alpha Compute
- Apply Rope Write KV
- Batch Evict Kernels
- Build Layout
- Causal Conv1d
- Common
- Context FMHA Runner
- Conversion
- Cute Dsl FMHA Runner
- Cute Dsl Gdn Runner
- Cute Dsl GEMM Runner
- Cute Dsl Ssd Runner
- Decoder XQA Runner
- Dequant
- Dequantize
- EAGLE Accept Kernels
- EAGLE Util Kernels
- Embedding Kernels
- FMHA Params V2
- Fp4 Quantize
- Gdn Kernel Utils
- Image Util Kernels
- Initialize Cos Sin Cache
- Int4 Groupwise GEMM
- Kernel
- Kernel Selector
- Kernels
- KV Cache Utils Kernels
- Marlin
- Marlin Dtypes
- Marlin Mma
- Marlin Template
- Marlin Template
- Moe Activation Kernels
- Moe Align Sum Kernels
- Moe Gather
- Moe Marlin
- Moe Marlin Indices Kernels
- Moe Sigmoid Group Topk Kernels
- Moe Topk Softmax Kernels
- Nvfp4 Moe Types
- Nvfp4 Dequant
- Nvfp4 Tensor
- Selective State Update
- Talker Mlp Kernels
- Util Kernels
- Vectorized Types
- Multimodal Module
- Plugins Module
- Profiling Module
- Runtime Module
- Sampler Module
- Tokenizer Module