All modules for which code is available

• tensorrt_llm._torch.async_llm
• tensorrt_llm._torch.auto_deploy.transform.graph_module_visualizer
• tensorrt_llm._torch.auto_deploy.transform.interface
• tensorrt_llm._torch.auto_deploy.transform.library.attention
• tensorrt_llm._torch.auto_deploy.transform.library.build_model
• tensorrt_llm._torch.auto_deploy.transform.library.cleanup_identity_dtype_cast
• tensorrt_llm._torch.auto_deploy.transform.library.cleanup_input_constraints
• tensorrt_llm._torch.auto_deploy.transform.library.cleanup_noop_add
• tensorrt_llm._torch.auto_deploy.transform.library.cleanup_noop_slice
• tensorrt_llm._torch.auto_deploy.transform.library.collectives
• tensorrt_llm._torch.auto_deploy.transform.library.compile_model
• tensorrt_llm._torch.auto_deploy.transform.library.eliminate_redundant_transposes
• tensorrt_llm._torch.auto_deploy.transform.library.export_to_gm
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_causal_conv
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_gdn_gating
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_mamba_a_log
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_quant
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_relu2_quant_nvfp4
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_rmsnorm_quant_fp8
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_rmsnorm_quant_nvfp4
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_rope_into_trtllm_attention
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_rope_mla
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_silu_mul
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_swiglu
• tensorrt_llm._torch.auto_deploy.transform.library.fuse_trtllm_attention_quant_fp8
• tensorrt_llm._torch.auto_deploy.transform.library.fused_add_rms_norm
• tensorrt_llm._torch.auto_deploy.transform.library.fused_moe
• tensorrt_llm._torch.auto_deploy.transform.library.fused_moe_mxfp4
• tensorrt_llm._torch.auto_deploy.transform.library.fusion
• tensorrt_llm._torch.auto_deploy.transform.library.gather_logits_before_lm_head
• tensorrt_llm._torch.auto_deploy.transform.library.hidden_states
• tensorrt_llm._torch.auto_deploy.transform.library.kvcache
• tensorrt_llm._torch.auto_deploy.transform.library.kvcache_transformers
• tensorrt_llm._torch.auto_deploy.transform.library.l2_norm
• tensorrt_llm._torch.auto_deploy.transform.library.load_weights
• tensorrt_llm._torch.auto_deploy.transform.library.mlir_elementwise_fusion
• tensorrt_llm._torch.auto_deploy.transform.library.moe_routing
• tensorrt_llm._torch.auto_deploy.transform.library.mrope_delta_cache
• tensorrt_llm._torch.auto_deploy.transform.library.multi_stream_attn
• tensorrt_llm._torch.auto_deploy.transform.library.multi_stream_gemm
• tensorrt_llm._torch.auto_deploy.transform.library.multi_stream_moe
• tensorrt_llm._torch.auto_deploy.transform.library.quantization
• tensorrt_llm._torch.auto_deploy.transform.library.quantize_moe
• tensorrt_llm._torch.auto_deploy.transform.library.rms_norm
• tensorrt_llm._torch.auto_deploy.transform.library.rope
• tensorrt_llm._torch.auto_deploy.transform.library.sharding
• tensorrt_llm._torch.auto_deploy.transform.library.sharding_ir
• tensorrt_llm._torch.auto_deploy.transform.library.ssm_cache
• tensorrt_llm._torch.auto_deploy.transform.library.visualization
• tensorrt_llm._torch.auto_deploy.transform.optimizer
• tensorrt_llm._torch.auto_deploy.transform.pipeline_cache.pipeline_cache
• tensorrt_llm.bindings.executor
• tensorrt_llm.conversation_params
• tensorrt_llm.disaggregated_params
• tensorrt_llm.executor.request
• tensorrt_llm.executor.result
• tensorrt_llm.executor.utils
• tensorrt_llm.llmapi.llm
• tensorrt_llm.llmapi.llm_args
• tensorrt_llm.llmapi.mm_encoder
• tensorrt_llm.llmapi.mpi_session
• tensorrt_llm.llmapi.thinking_budget
• tensorrt_llm.models.modeling_utils
• tensorrt_llm.quantization.mode
• tensorrt_llm.sampling_params
• tensorrt_llm.scheduling_params