All modules for which code is available

• 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.models.baichuan.model
• tensorrt_llm.models.bert.model
• tensorrt_llm.models.bloom.model
• tensorrt_llm.models.chatglm.model
• tensorrt_llm.models.enc_dec.model
• tensorrt_llm.models.falcon.model
• tensorrt_llm.models.gemma.model
• tensorrt_llm.models.gpt.model
• tensorrt_llm.models.gptj.model
• tensorrt_llm.models.gptneox.model
• tensorrt_llm.models.llama.model
• tensorrt_llm.models.mamba.model
• tensorrt_llm.models.medusa.model
• tensorrt_llm.models.modeling_utils
• tensorrt_llm.models.mpt.model
• tensorrt_llm.models.opt.model
• tensorrt_llm.models.phi.model
• tensorrt_llm.models.quantized.quant
• tensorrt_llm.models.qwen.model
• tensorrt_llm.plugin.plugin
• tensorrt_llm.quantization.mode
• tensorrt_llm.quantization.quantize_by_ammo
• tensorrt_llm.runtime.generation
• tensorrt_llm.runtime.kv_cache_manager
• tensorrt_llm.runtime.model_runner
• tensorrt_llm.runtime.model_runner_cpp
• tensorrt_llm.runtime.session