Unverified Commit 9a3101b2 authored by Charlie Fu's avatar Charlie Fu Committed by GitHub
Browse files

[Rocm][CI] Fix DeekSeek V2-Lite Accuracy CI (#29135)


Signed-off-by: default avatarcharlifu <charlifu@amd.com>
parent d5dbdbfc
...@@ -17,7 +17,17 @@ wait_for_server() { ...@@ -17,7 +17,17 @@ wait_for_server() {
} }
MODEL="deepseek-ai/DeepSeek-V2-lite" MODEL="deepseek-ai/DeepSeek-V2-lite"
BACKENDS=("deepep_high_throughput" "deepep_low_latency")
# Set BACKENDS based on platform
if command -v rocm-smi &> /dev/null || [[ -d /opt/rocm ]] || [[ -n "${ROCM_PATH:-}" ]]; then
# ROCm platform
BACKENDS=("allgather_reducescatter")
# Disable MOE padding for ROCm since it is causing eplb to fail
export VLLM_ROCM_MOE_PADDING=0
else
# Non-ROCm platform (CUDA/other)
BACKENDS=("deepep_high_throughput" "deepep_low_latency")
fi
cleanup() { cleanup() {
if [[ -n "${SERVER_PID:-}" ]] && kill -0 "${SERVER_PID}" 2>/dev/null; then if [[ -n "${SERVER_PID:-}" ]] && kill -0 "${SERVER_PID}" 2>/dev/null; then
......
...@@ -17,7 +17,16 @@ wait_for_server() { ...@@ -17,7 +17,16 @@ wait_for_server() {
} }
MODEL="QWen/Qwen3-30B-A3B-FP8" MODEL="QWen/Qwen3-30B-A3B-FP8"
BACKENDS=("deepep_high_throughput" "deepep_low_latency") # Set BACKENDS based on platform
if command -v rocm-smi &> /dev/null || [[ -d /opt/rocm ]] || [[ -n "${ROCM_PATH:-}" ]]; then
# ROCm platform
BACKENDS=("allgather_reducescatter")
# Disable MOE padding for ROCm since it is causing eplb to fail
export VLLM_ROCM_MOE_PADDING=0
else
# Non-ROCm platform (CUDA/other)
BACKENDS=("deepep_high_throughput" "deepep_low_latency")
fi
cleanup() { cleanup() {
if [[ -n "${SERVER_PID:-}" ]] && kill -0 "${SERVER_PID}" 2>/dev/null; then if [[ -n "${SERVER_PID:-}" ]] && kill -0 "${SERVER_PID}" 2>/dev/null; then
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment