diff --git a/experiments/dsv4_pro6000_sglang_tp_dp_matrix/adaptive_config.env b/experiments/dsv4_pro6000_sglang_tp_dp_matrix/adaptive_config.env index 4085397..1eda1f0 100644 --- a/experiments/dsv4_pro6000_sglang_tp_dp_matrix/adaptive_config.env +++ b/experiments/dsv4_pro6000_sglang_tp_dp_matrix/adaptive_config.env @@ -1,6 +1,6 @@ # Adaptive concurrency search settings. # -# For each fixed (TP, DP, ISL, DSL), probe: +# For each fixed (TP, DP, ISL, OSL), probe: # C = start, start * multiplier, ... up to max # and stop after Total TPS has less than TPS_MIN_GAIN_PCT meaningful growth for # PLATEAU_PATIENCE consecutive points. @@ -21,7 +21,7 @@ PLATEAU_PATIENCE="${PLATEAU_PATIENCE:-2}" # random-ids to use generated token IDs without a ShareGPT seed dataset. BENCH_DATASET_NAME="${BENCH_DATASET_NAME:-random}" # SGLang interprets 0.0 as Uniform[1, requested_len]. Use 1.0 for fixed -# ISL/DSL points; lower values intentionally benchmark a length distribution. +# ISL/OSL points; lower values intentionally benchmark a length distribution. RANDOM_RANGE_RATIO="${RANDOM_RANGE_RATIO:-1.0}" # Before each measured point, warm up with the same concurrency so lazy kernel # compilation and CUDA graph capture are excluded from TTFT/TPS. 0 means no @@ -39,11 +39,11 @@ SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-1800}" GPU_MEM_SAMPLE_INTERVAL_S="${GPU_MEM_SAMPLE_INTERVAL_S:-1}" # Optional space-separated filters, useful for smoke tests: -# TP_LIST="8" ISL_LIST="1024" DSL_LIST="128" +# TP_LIST="8" ISL_LIST="1024" OSL_LIST="128" TP_LIST="${TP_LIST:-}" ISL_LIST="${ISL_LIST:-}" -DSL_LIST="${DSL_LIST:-}" +OSL_LIST="${OSL_LIST:-}" DRY_RUN="${DRY_RUN:-0}" -# Counts ISL/DSL shapes per TP/DP config, not individual concurrency probes. +# Counts ISL/OSL shapes per TP/DP config, not individual concurrency probes. GRID_LIMIT="${GRID_LIMIT:-0}" diff --git a/experiments/dsv4_pro6000_sglang_tp_dp_matrix/run_adaptive_concurrency.sh b/experiments/dsv4_pro6000_sglang_tp_dp_matrix/run_adaptive_concurrency.sh index 90f7827..0979a46 100755 --- a/experiments/dsv4_pro6000_sglang_tp_dp_matrix/run_adaptive_concurrency.sh +++ b/experiments/dsv4_pro6000_sglang_tp_dp_matrix/run_adaptive_concurrency.sh @@ -1,5 +1,5 @@ #!/usr/bin/env bash -# Find the Total-TPS saturation concurrency for each SGLang TP/DP/ISL/DSL shape. +# Find the Total-TPS saturation concurrency for each SGLang TP/DP/ISL/OSL shape. set -Eeuo pipefail SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" @@ -130,7 +130,7 @@ engine_detect_oom() { engine_run_bench() { local isl="$1" - local dsl="$2" + local osl="$2" local concurrency="$3" local num_prompts="$4" local output_file="$5" @@ -142,7 +142,7 @@ engine_run_bench() { --port "$ENGINE_PORT" --dataset-name "$BENCH_DATASET_NAME" --random-input-len "$isl" - --random-output-len "$dsl" + --random-output-len "$osl" --random-range-ratio "$RANDOM_RANGE_RATIO" --num-prompts "$num_prompts" --max-concurrency "$concurrency"