TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
[TensorRT-LLM] TensorRT-LLM version: 0.9.0.dev2024020600[TensorRT-LLM] TensorRT-LLM version: 0.9.0.dev2024020600[TensorRT-LLM] TensorRT-LLM version: 0.9.0.dev2024020600free(): invalid pointer [95e079756bc2:03949] Process received signal [95e079756bc2:03949] Signal: Aborted (6) [95e079756bc2:03949] Signal code: (-6) [95e079756bc2:03949] [ 0] /usr/lib/x86_64-linux-gnu/libc.so.6(+0x42520)[0x7f754a216520] [95e079756bc2:03949] [ 1] /usr/lib/x86_64-linux-gnu/libc.so.6(pthread_kill+0x12c)[0x7f754a26a9fc] [95e079756bc2:03949] [ 2] /usr/lib/x86_64-linux-gnu/libc.so.6(raise+0x16)[0x7f754a216476] [95e079756bc2:03949] [ 3] /usr/lib/x86_64-linux-gnu/libc.so.6(abort+0xd3)[0x7f754a1fc7f3] [95e079756bc2:03949] [ 4] /usr/lib/x86_64-linux-gnu/libc.so.6(+0x89676)[0x7f754a25d676] [95e079756bc2:03949] [ 5] /usr/lib/x86_64-linux-gnu/libc.so.6(+0xa0cfc)[0x7f754a274cfc] [95e079756bc2:03949] [ 6] /usr/lib/x86_64-linux-gnu/libc.so.6(+0xa2a44)[0x7f754a276a44] [95e079756bc2:03949] [ 7] /usr/lib/x86_64-linux-gnu/libc.so.6(free+0x73)[0x7f754a279453] [95e079756bc2:03949] [ 8] /opt/tritonserver/backends/python/triton_python_backend_stub(+0x6fd54)[0x55e2133c5d54] [95e079756bc2:03949] [ 9] /opt/tritonserver/backends/python/triton_python_backend_stub(+0x25de3)[0x55e21337bde3] [95e079756bc2:03949] [10] /usr/lib/x86_64-linux-gnu/libc.so.6(+0x29d90)[0x7f754a1fdd90] [95e079756bc2:03949] [11] /usr/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80)[0x7f754a1fde40] [95e079756bc2:03949] [12] /opt/tritonserver/backends/python/triton_python_backend_stub(+0x26b45)[0x55e21337cb45] [95e079756bc2:03949] End of error message free(): invalid pointer