[djl] patch release for 0.32.0 TRT-LLM DLC, update available_images.md (#4612)

Author: ethnzhng

available_images.md

@@ -193,6 +193,7 @@ Starting LMI V10 (0.28.0), we are changing the name from LMI DeepSpeed DLC to LM
 | Framework                                                                                                                   | Job Type  | Accelerator | Python Version Options | Example URL                                                                               |
 |-----------------------------------------------------------------------------------------------------------------------------|-----------|-------------|------------------------|-------------------------------------------------------------------------------------------|
 | DJLServing 0.32.0 with LMI Dist 13.0.0, vLLM 0.7.1, 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:0.32.0-lmi14.0.0-cu126         |
+| DJLServing 0.32.0 with TensorRT-LLM 0.12.0, HuggingFace Transformers 4.44.2, and HuggingFace Accelerate 0.32.1              | inference | GPU         | 3.10 (py310)           | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.32.0-tensorrtllm0.12.0-cu125 |
 | 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-cu125 |

release_images_inference.yml

@@ -126,10 +126,9 @@ release_images:
     arch_type: "x86"
     inference:
       device_types: [ "gpu" ]
-      python_versions: [ "py312" ]
-      os_version: "ubuntu22.04"
-      lmi_version: "14.0.0"
-      cuda_version: "cu126"
+      python_versions: [ "py310" ]
+      os_version: "ubuntu24.04"
+      tensorrtllm_version: "0.12.0"
       example: False
       disable_sm_tag: True
       force_release: False