Merge branch 'main' of https://gitee.com/yy-fighting/sskj

experiments/h20/dsv4_h20_sglang_tp_dp_matrix/adaptive_config.env

@@ -15,6 +15,12 @@ NUM_PROMPTS_MULTIPLIER="${NUM_PROMPTS_MULTIPLIER:-5}"
 TPS_MIN_GAIN_PCT="${TPS_MIN_GAIN_PCT:-2.0}"
 PLATEAU_PATIENCE="${PLATEAU_PATIENCE:-2}"
 
+# TTFT SLO early-stop settings.
+# When ttft_p95_ms exceeds TTFT_SLO_MS, stop searching the current (ISL, OSL)
+# shape and move on to the next scenario.
+TTFT_SLO_MS="${TTFT_SLO_MS:-4000}"
+ENABLE_TTFT_SLO_STOP="${ENABLE_TTFT_SLO_STOP:-1}"
+
 # Keep the same random workload semantics as the fixed matrix baseline.
 # DATASET_PATH must contain at least SEARCH_MAX_CONCURRENCY times
 # NUM_PROMPTS_MULTIPLIER valid two-turn conversations. Set this explicitly to

experiments/h20/dsv4_h20_sglang_tp_dp_matrix/run_adaptive_concurrency.sh

@@ -6,15 +6,15 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
 
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/adaptive_config.env"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/adaptive_bench_lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/adaptive_bench_lib.sh"
 
 ENGINE="sglang"
 ENGINE_PORT="$SGLANG_PORT"

experiments/h20/dsv4_h20_sglang_tp_dp_matrix/run_adaptive_concurrency_add16.sh

@@ -6,15 +6,15 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
 
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/adaptive_config.env"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/adaptive_bench_lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/adaptive_bench_lib.sh"
 
 ENGINE="sglang"
 ENGINE_PORT="$SGLANG_PORT"

experiments/h20/dsv4_h20_sglang_tp_dp_matrix/run_bench.sh

@@ -6,9 +6,9 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
 
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 
@@ -522,7 +522,7 @@ run_parallel_config() {
 
   # Parse results.
   log "parsing ${config_label} results"
-  "$PYTHON" "${SCRIPT_DIR}/../../scripts/common/parse_backend.py" "$result_root" --backend sglang \
+  "$PYTHON" "${SCRIPT_DIR}/../../../scripts/common/parse_backend.py" "$result_root" --backend sglang \
     >> "${phase_log_dir}/parse.log" 2>&1 || {
       log "WARNING: parser failed for ${config_label}; see ${phase_log_dir}/parse.log"
     }

experiments/h20/dsv4_h20_vllm_tp_dp_matrix/adaptive_config.env

@@ -15,6 +15,12 @@ NUM_PROMPTS_MULTIPLIER="${NUM_PROMPTS_MULTIPLIER:-5}"
 TPS_MIN_GAIN_PCT="${TPS_MIN_GAIN_PCT:-2.0}"
 PLATEAU_PATIENCE="${PLATEAU_PATIENCE:-2}"
 
+# TTFT SLO early-stop settings.
+# When ttft_p95_ms exceeds TTFT_SLO_MS, stop searching the current (ISL, OSL)
+# shape and move on to the next scenario.
+TTFT_SLO_MS="${TTFT_SLO_MS:-4000}"
+ENABLE_TTFT_SLO_STOP="${ENABLE_TTFT_SLO_STOP:-1}"
+
 # Keep the same random workload semantics as the fixed matrix baseline.
 # DATASET_PATH must contain at least SEARCH_MAX_CONCURRENCY times
 # NUM_PROMPTS_MULTIPLIER valid two-turn conversations. Set this explicitly to

experiments/h20/dsv4_h20_vllm_tp_dp_matrix/compare.py

@@ -18,7 +18,7 @@ def load_result(result_root: Path) -> dict:
 
 
 def slo_status(ttft_p95_ms: float, tpot_mean_ms: float,
-               ttft_limit_ms: float = 3000.0, tpot_limit_ms: float = 50.0) -> str:
+               ttft_limit_ms: float = 4000.0, tpot_limit_ms: float = 50.0) -> str:
     ttft_ok = ttft_p95_ms < ttft_limit_ms
     tpot_ok = tpot_mean_ms < tpot_limit_ms
     if ttft_ok and tpot_ok:
@@ -42,7 +42,7 @@ def main():
     parser = argparse.ArgumentParser()
     parser.add_argument("--run-root", type=Path, required=True)
     parser.add_argument("-o", "--output", type=Path, default=Path("comparison.md"))
-    parser.add_argument("--ttft-limit", type=float, default=3000.0)
+    parser.add_argument("--ttft-limit", type=float, default=4000.0)
     parser.add_argument("--tpot-limit", type=float, default=50.0)
     args = parser.parse_args()
 

experiments/h20/dsv4_h20_vllm_tp_dp_matrix/run_adaptive_concurrency.sh

@@ -6,15 +6,15 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
 
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/adaptive_config.env"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/adaptive_bench_lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/adaptive_bench_lib.sh"
 
 ENGINE="vllm"
 ENGINE_PORT="$VLLM_PORT"

experiments/h20/dsv4_h20_vllm_tp_dp_matrix/run_adaptive_concurrency_add16.sh

@@ -6,15 +6,15 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
 
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/adaptive_config.env"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/adaptive_bench_lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/adaptive_bench_lib.sh"
 
 ENGINE="vllm"
 ENGINE_PORT="$VLLM_PORT"

experiments/h20/dsv4_h20_vllm_tp_dp_matrix/run_bench.sh

@@ -6,9 +6,9 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
 
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/lib.sh"
 # shellcheck source=/dev/null
-source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+source "${SCRIPT_DIR}/../../../scripts/common/platform.sh"
 # shellcheck source=/dev/null
 source "${SCRIPT_DIR}/config.env"
 
@@ -512,7 +512,7 @@ run_parallel_config() {
 
   # Parse results.
   log "parsing ${config_label} results"
-  "$PYTHON" "${SCRIPT_DIR}/../../scripts/common/parse_backend.py" "$result_root" --backend vllm \
+  "$PYTHON" "${SCRIPT_DIR}/../../../scripts/common/parse_backend.py" "$result_root" --backend vllm \
     >> "${phase_log_dir}/parse.log" 2>&1 || {
       log "WARNING: parser failed for ${config_label}; see ${phase_log_dir}/parse.log"
     }