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.builder
• tensorrt_llm.disaggregated_params
• tensorrt_llm.executor.request
• tensorrt_llm.executor.result
• tensorrt_llm.executor.utils
• tensorrt_llm.functional
• tensorrt_llm.layers.activation
• tensorrt_llm.layers.attention
• tensorrt_llm.layers.cast
• tensorrt_llm.layers.conv
• tensorrt_llm.layers.embedding
• tensorrt_llm.layers.linear
• tensorrt_llm.layers.mlp
• tensorrt_llm.layers.normalization
• tensorrt_llm.layers.pooling
• tensorrt_llm.llmapi.build_cache
• 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.baichuan.model
• tensorrt_llm.models.bert.model
• tensorrt_llm.models.bloom.model
• tensorrt_llm.models.chatglm.config
• tensorrt_llm.models.chatglm.model
• tensorrt_llm.models.clip.model
• tensorrt_llm.models.cogvlm.config
• tensorrt_llm.models.cogvlm.model
• tensorrt_llm.models.commandr.model
• tensorrt_llm.models.dbrx.config
• tensorrt_llm.models.dbrx.model
• tensorrt_llm.models.deepseek_v1.model
• tensorrt_llm.models.deepseek_v2.model
• tensorrt_llm.models.dit.model
• tensorrt_llm.models.eagle.model
• tensorrt_llm.models.enc_dec.model
• tensorrt_llm.models.falcon.config
• tensorrt_llm.models.falcon.model
• tensorrt_llm.models.gemma.config
• tensorrt_llm.models.gemma.model
• tensorrt_llm.models.gpt.config
• tensorrt_llm.models.gpt.model
• tensorrt_llm.models.gptj.config
• tensorrt_llm.models.gptj.model
• tensorrt_llm.models.gptneox.model
• tensorrt_llm.models.llama.config
• tensorrt_llm.models.llama.model
• tensorrt_llm.models.mamba.model
• tensorrt_llm.models.medusa.config
• tensorrt_llm.models.medusa.model
• tensorrt_llm.models.mllama.model
• tensorrt_llm.models.mmdit_sd3.model
• tensorrt_llm.models.modeling_utils
• tensorrt_llm.models.mpt.model
• tensorrt_llm.models.multimodal_encoders.config
• tensorrt_llm.models.multimodal_encoders.model
• tensorrt_llm.models.opt.model
• tensorrt_llm.models.phi.model
• tensorrt_llm.models.phi3.model
• tensorrt_llm.models.recurrentgemma.model
• tensorrt_llm.models.redrafter.model
• tensorrt_llm.plugin.plugin
• tensorrt_llm.quantization.mode
• tensorrt_llm.quantization.quantize_by_modelopt
• tensorrt_llm.runtime.enc_dec_model_runner
• tensorrt_llm.runtime.generation
• tensorrt_llm.runtime.kv_cache_manager
• tensorrt_llm.runtime.model_runner
• tensorrt_llm.runtime.model_runner_cpp
• tensorrt_llm.runtime.multimodal_model_runner
• tensorrt_llm.runtime.session
• tensorrt_llm.sampling_params
• tensorrt_llm.scheduling_params