dsv4_h200_sglang_tp_dp_matrix: sample only low/high concurrency, use RUNTIME_BASE for self-contained runtime files

experiments/dsv4_h200_sglang_tp_dp_matrix/config.env

@@ -23,6 +23,10 @@ USE_DOCKER_CLIENT="${USE_DOCKER_CLIENT:-1}"
 
 export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,2,3,4,5,6,7}"
 
+# Runtime working directory for logs, pid files, and tmp. Defaults to a local
+# directory under this experiment so the benchmark is self-contained.
+RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"
+
 # Parallel configurations to test. Format: "TP DP"
 declare -a PARALLEL_CONFIGS=(
   "2 4"

experiments/dsv4_h200_sglang_tp_dp_matrix/generate_scenarios.py

@@ -15,23 +15,16 @@ from pathlib import Path
 
 
 def sample_concurrency(low: int, high: int, target: int) -> list[int]:
-    """Return a sorted list of concurrency values in [low, high].
+    """Return only the low and high concurrency values in [low, high].
 
-    If the range is small, return every integer. Otherwise sample roughly
-    `target` points linearly between low and high (inclusive).
+    For the TP×DP matrix we only need the two endpoints of the concurrency
+    range (e.g. 1 and 128 for ISL=1024). The `target` argument is kept for
+    API compatibility but is ignored.
     """
     assert 1 <= low <= high, f"invalid concurrency range: {low}-{high}"
-    if high - low + 1 <= target:
-        return list(range(low, high + 1))
-
-    points = set()
-    points.add(low)
-    points.add(high)
-    step = (high - low) / (target - 1)
-    for i in range(1, target - 1):
-        v = low + round(step * i)
-        points.add(max(low, min(high, v)))
-    return sorted(points)
+    if low == high:
+        return [low]
+    return [low, high]
 
 
 def generate_scenarios(matrix_path: Path, mode: str, target_samples: int) -> list[dict]:

experiments/dsv4_h200_sglang_tp_dp_matrix/run_bench.sh

@@ -48,7 +48,7 @@ stop_server() {
   local tp="$1"
   local dp="$2"
 
-  local pid_file="/data/user1/yy/${EXPERIMENT}_sglang_tp${tp}_dp${dp}.pid"
+  local pid_file="${RUNTIME_BASE}/${EXPERIMENT}_sglang_tp${tp}_dp${dp}.pid"
   if [[ -f "$pid_file" ]]; then
     local pid
     pid="$(cat "$pid_file")"

experiments/dsv4_h200_sglang_tp_dp_matrix/start_sglang_docker.sh

@@ -13,15 +13,15 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 
-cd /data/user1/yy
-mkdir -p logs
+RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"
+mkdir -p "${RUNTIME_BASE}/logs" "${RUNTIME_BASE}/tmp"
 
 IMAGE="${DOCKER_IMAGE:-lmsysorg/sglang:latest}"
 PORT="${SGLANG_PORT:-30031}"
 NAME="${EXPERIMENT}_sglang_tp${TP}_dp${DP}"
-PID_FILE="/data/user1/yy/${EXPERIMENT}_sglang_tp${TP}_dp${DP}.pid"
+PID_FILE="${RUNTIME_BASE}/${EXPERIMENT}_sglang_tp${TP}_dp${DP}.pid"
 
-LOG="/data/user1/yy/logs/${EXPERIMENT}_sglang_docker_tp${TP}_dp${DP}_$(date +%Y%m%d_%H%M%S).log"
+LOG="${RUNTIME_BASE}/logs/${EXPERIMENT}_sglang_docker_tp${TP}_dp${DP}_$(date +%Y%m%d_%H%M%S).log"
 rm -f "$PID_FILE"
 
 # Clean up any stale container with the same name.
@@ -64,7 +64,7 @@ nohup docker run --rm \
   --entrypoint sglang \
   -p "${PORT}:${PORT}" \
   -v "${MODEL_PATH}:${MODEL_PATH}:ro" \
-  -v /data/user1/yy/tmp:/tmp \
+  -v "${RUNTIME_BASE}/tmp:/tmp" \
   -e CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES}" \
   -e PYTHONUNBUFFERED=1 \
   "$IMAGE" \

experiments/dsv4_h200_sglang_tp_dp_matrix/start_sglang_dp.sh

@@ -18,17 +18,17 @@ if [[ "${USE_DOCKER:-1}" == "1" ]]; then
   exec "${SCRIPT_DIR}/start_sglang_docker.sh" "$@"
 fi
 
-cd /data/user1/yy
-mkdir -p logs
+RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"
+mkdir -p "${RUNTIME_BASE}/logs" "${RUNTIME_BASE}/tmp"
 
 VENV="${VENV_CLIENT}"
 export PATH="$VENV/bin:$PATH"
 export PYTHONUNBUFFERED=1
-export TMPDIR=/data/user1/yy/tmp
+export TMPDIR="${RUNTIME_BASE}/tmp"
 export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES}"
 
-LOG="/data/user1/yy/logs/${EXPERIMENT}_sglang_tp${TP}_dp${DP}_$(date +%Y%m%d_%H%M%S).log"
-PID_FILE="/data/user1/yy/${EXPERIMENT}_sglang_tp${TP}_dp${DP}.pid"
+LOG="${RUNTIME_BASE}/logs/${EXPERIMENT}_sglang_tp${TP}_dp${DP}_$(date +%Y%m%d_%H%M%S).log"
+PID_FILE="${RUNTIME_BASE}/${EXPERIMENT}_sglang_tp${TP}_dp${DP}.pid"
 
 rm -f "$PID_FILE"