runtime failed with core dumped #59
Description
Problem Description
- env:
GPU Marketing Name: AMD Radeon Graphics
GPU Name: amdgcn-amd-amdhsa--gfx942:sramecc+:xnack-
base image: rocm/pytorch-private:vllm0.4.3_06_21_alibaba_fixwvsplitk_ll2_train_csrikris_06_25- runtime steps
chmod +x /usr/local/lib/runTracher.sh
cd rocpd_python/
python3 -m pip install .
runTracer.sh python3 /workspace/vllm/benchmarks/benchmark_latency.py --model /workspace/Qwen2-7B/ --input-len 32 --output-len 128 --batch-size 16 --dtype float16 --enforce-eager --num-iters-warmup 2 --num-iters 10 - output errors:
...
rocpd_op: 0
rocpd_api_ops: 0
rocpd_kernelapi: 0
rocpd_copyapi: 0
rocpd_api: 0
rocpd_string: 0
rpd_tracer: finalized in 1221.910687 ms
double free or corruption (!prev)
/usr/local/bin/runTracer.sh: line 43: 5233 Aborted (core dumped) LD_PRELOAD=librpd_tracer.so "$@"there is core dumped error when run tracing. can someone help to verify ? thanks a lot
Operating System
Ubuntu 20.04.6 LTS (Focal Fossa)
CPU
Intel(R) Xeon(R) Platinum 8480C
GPU
AMD Instinct MI300X
ROCm Version
ROCm 6.1.0
ROCm Component
No response
Steps to Reproduce
No response
(Optional for Linux users) Output of /opt/rocm/bin/rocminfo --support
No response
Additional Information
No response