Release notes from TensorRT-LLM
Articles about Release notes from TensorRT-LLM
Release v1.3.0rc29 · NVIDIA/TensorRT-LLM
Highlights Model Support Support Qwen3.5 checkpoints with global FP8 scales across model loading paths #19519 Optimize Gemma4 vision rotary embeddings without a GEMM operation #19571 Enable the CuTeDSL MoE backend for Kimi K3 NVFP4 SiTU #19003 Expose Nemotron-H vision-language LoRA configuration for supported inference paths
Release v1.3.0rc28 · NVIDIA/TensorRT-LLM
Highlights Known Issues Multi-node inference may fail during startup when a requested parallel mapping spans nodes or request payloads reference caller-local Python modules. Disaggregated serving may fail to start when an advertised hostname does not resolve to a bindable IPv4 address. Use a hostname that resolves to a local IPv4 interface. Qwen3.5-4B may lose accuracy with context pipeline parallelism and a different generation tensor-parallel layout.