diff --git a/available_images.md b/available_images.md index 2ac404863edd..42c54c3e27ff 100644 --- a/available_images.md +++ b/available_images.md @@ -193,7 +193,7 @@ Starting LMI V10 (0.28.0), we are changing the name from LMI DeepSpeed DLC to LM |-----------------------------------------------------------------------------------------------------------------------------|-----------|-------------|------------------------|-------------------------------------------------------------------------------------------| | DJLServing 0.31.0 with LMI Dist 13.0.0, vLLM 0.6.3.post1, HuggingFace Transformers 4.45.2, and HuggingFace Accelerate 1.0.1 | inference | GPU | 3.11 (py311) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.31.0-lmi13.0.0-cu124 | | DJLServing 0.30.0 with LMI Dist 12.0.0, vLLM 0.6.2, HuggingFace Transformers 4.45.2, and HuggingFace Accelerate 1.0.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.30.0-lmi12.0.0-cu124 | -| DJLServing 0.30.0 with TensorRT-LLM 0.12.0, HuggingFace Transformers 4.44.2, and HuggingFace Accelerate 0.33.0 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.30.0-tensorrtllm0.12.0 | +| DJLServing 0.30.0 with TensorRT-LLM 0.12.0, HuggingFace Transformers 4.44.2, and HuggingFace Accelerate 0.33.0 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.30.0-tensorrtllm0.12.0-cu125 | | DJLServing 0.30.0 with Neuron SDK 2.20.1, TransformersNeuronX 0.12.313, and HuggingFace Transformers 4.45.2 | inference | Neuron | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.30.0-neuronx-sdk2.20.1 | | DJLServing 0.29.0 with TensorRT-LLM 0.11.0, HuggingFace Transformers 4.42.4, and HuggingFace Accelerate 0.32.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-tensorrtllm0.11.0-cu124 | | DJLServing 0.29.0 with LMI Dist 11.0.0, HuggingFace Transformers 4.43.2, HuggingFace Accelerate 0.32.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-lmi11.0.0-cu124 |