feat(p800): add max context length exploration experiment

Add experiments/dsv4_p800_max_context_length/ to find the longest input context that P800 SGLang INT8 can serve for DeepSeek-V4-Flash-INT8. - Docker-based server start with dynamic --context-length. - Single-request, single-output-token probes for each candidate length. - Records success/failure, server args, and metrics per length. - Generates results.json and report.md summarizing the max supported length. - Smoke-tested at 4096 tokens successfully.
2026-07-09 03:30:09 +00:00 · 2026-07-09 03:30:09 +00:00 · 3694614dd9
commit 3694614dd9
parent 8324d944f2
29 changed files with 3566 additions and 0 deletions
--- a/experiments/dsv4_p800_max_context_length/README.md
+++ b/experiments/dsv4_p800_max_context_length/README.md
@ -0,0 +1,59 @@
+# DSV4 P800 最大上下文长度探索实验
+
+在 8x Kunlun P800 XPU 上，逐步增大输入长度，测试 SGLang serving `DeepSeek-V4-Flash-INT8` 时能稳定处理的最长上下文。
+
+## 目的
+
+- 找到 P800 + SGLang INT8 在 TP=8 配置下，单请求最多能支持多长的输入 token。
+- 每个长度只跑 1 个请求、输出 1 个 token，尽量减少 decode 阶段显存干扰。
+- 每次测试单独启动 server，并把 `context-length` 刚好设为 `target_len + CONTEXT_PAD`，避免预分配过大。
+
+## 默认候选长度
+
+```text
+4096, 8192, 16384, 32768, 65536, 131072, 262144, 524288
+```
+
+可以通过环境变量覆盖：
+
+```bash
+CANDIDATE_LENS=(4096 8192 16384) bash run_bench.sh
+```
+
+## 控制变量
+
+| 维度 | 配置 |
+|---|---|
+| 硬件 | 8x Kunlun P800 XPU，TP=8 |
+| 模型 | `DeepSeek-V4-Flash-INT8`（`w8a8_int8`） |
+| 输入长度 | `--random-input-len $target_len --random-range-ratio 1.0` |
+| 输出长度 | 1 |
+| 并发 / 请求数 | 1 / 1 |
+| 压测客户端 | 容器内 `sglang.bench_serving --backend sglang` |
+
+> `--random-range-ratio 1.0` 确保输入长度固定为 `target_len`，而不是默认的 `[1, target_len]` 均匀分布。
+
+## 快速运行
+
+```bash
+bash experiments/dsv4_p800_max_context_length/run_bench.sh
+```
+
+结果保存在 `experiments/dsv4_p800_max_context_length/results/<RUN_ID>/`：
+
+```
+results/<RUN_ID>/
+├── results.json
+├── report.md
+└── raw_outputs/      # gitignored
+```
+
+## 产物说明
+
+- `results.json`：每个候选长度的尝试记录，包括 `success`、TTFT/TPOT/E2E 指标、`server_args`。
+- `report.md`：汇总表格，以及 SGLang INT8 最终支持的最大输入长度。
+
+## 环境
+
+- Docker image: `iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260511_4202`
+- Container Python: `/root/miniconda/envs/python310_torch25_cuda/bin/python`
--- a/experiments/dsv4_p800_max_context_length/config.env
+++ b/experiments/dsv4_p800_max_context_length/config.env
@ -0,0 +1,43 @@
+# Common configuration for the max context length exploration on P800.
+# All values can be overridden via environment variables.
+
+EXPERIMENT="dsv4_p800_max_context_length"
+MODEL_NAME="DeepSeek-V4-Flash-INT8"
+MODEL_PATH="/data1/models/DeepSeek-V4-Flash-INT8"
+SERVED_MODEL_NAME="deepseek-v4-flash-int8"
+
+# Port must differ from other running experiments.
+PORT="${PORT:-30013}"
+
+# We want exact input lengths, so fix the random range ratio to 1.0.
+OUTPUT_LEN="${OUTPUT_LEN:-1}"
+NUM_PROMPTS="${NUM_PROMPTS:-1}"
+MAX_CONCURRENCY="${MAX_CONCURRENCY:-1}"
+REQUEST_RATE="${REQUEST_RATE:-10000}"
+
+# Padding added to target length when setting server context length.
+CONTEXT_PAD="${CONTEXT_PAD:-1024}"
+
+# Candidate input lengths (tokens). Override via CANDIDATE_LENS env var.
+# Examples:
+#   CANDIDATE_LENS="4096 8192 16384" bash run_bench.sh
+#   CANDIDATE_LENS=(4096 8192 16384) bash run_bench.sh
+if [[ -z "${CANDIDATE_LENS:-}" ]]; then
+  declare -a CANDIDATE_LENS=(
+    4096
+    8192
+    16384
+    32768
+    65536
+    131072
+    262144
+    524288
+  )
+elif ! declare -p CANDIDATE_LENS 2>/dev/null | grep -q '^declare -a'; then
+  # Normalize string-form arrays: remove surrounding parentheses and commas.
+  _CAND_STR="${CANDIDATE_LENS#(}"
+  _CAND_STR="${_CAND_STR%)}"
+  _CAND_STR="${_CAND_STR//,/}"
+  read -ra CANDIDATE_LENS <<< "$_CAND_STR"
+  unset _CAND_STR
+fi
--- a/experiments/dsv4_p800_max_context_length/extract_metrics.py
+++ b/experiments/dsv4_p800_max_context_length/extract_metrics.py
@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+"""Extract a compact metrics dict from a sglang.bench_serving JSONL output.
+
+Usage:
+    python3 extract_metrics.py <raw_jsonl_path>
+"""
+import json
+import sys
+from pathlib import Path
+
+
+def parse_jsonl(path: Path) -> dict | None:
+    with open(path, "r", encoding="utf-8") as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                return json.loads(line)
+            except json.JSONDecodeError:
+                continue
+    return None
+
+
+def compute(data: dict) -> dict:
+    return {
+        "success_count": data.get("completed", 0),
+        "total_count": len(data.get("input_lens", [])),
+        "duration_s": data.get("duration", 0.0),
+        "request_throughput": data.get("request_throughput", 0.0),
+        "input_token_throughput": data.get("input_throughput", 0.0),
+        "output_token_throughput": data.get("output_throughput", 0.0),
+        "total_input_tokens": data.get("total_input_tokens", 0),
+        "total_output_tokens": data.get("total_output_tokens", 0),
+        "e2e_ms": {
+            "mean": data.get("mean_e2e_latency_ms", 0.0),
+            "p50": data.get("median_e2e_latency_ms", 0.0),
+            "p90": data.get("p90_e2e_latency_ms", 0.0),
+            "p95": data.get("p95_e2e_latency_ms", 0.0),
+            "p99": data.get("p99_e2e_latency_ms", 0.0),
+        },
+        "ttft_ms": {
+            "mean": data.get("mean_ttft_ms", 0.0),
+            "p50": data.get("median_ttft_ms", 0.0),
+            "p90": data.get("p90_ttft_ms", 0.0),
+            "p95": data.get("p95_ttft_ms", 0.0),
+            "p99": data.get("p99_ttft_ms", 0.0),
+        },
+        "tpot_ms": {
+            "mean": data.get("mean_tpot_ms", 0.0),
+            "p50": data.get("median_tpot_ms", 0.0),
+            "p90": data.get("p90_tpot_ms", 0.0),
+            "p95": data.get("p95_tpot_ms", 0.0),
+            "p99": data.get("p99_tpot_ms", 0.0),
+        },
+        "itl_ms": {
+            "mean": data.get("mean_itl_ms", 0.0),
+            "p50": data.get("median_itl_ms", 0.0),
+            "p90": data.get("p90_itl_ms", 0.0),
+            "p95": data.get("p95_itl_ms", 0.0),
+            "p99": data.get("p99_itl_ms", 0.0),
+        },
+    }
+
+
+def main():
+    path = Path(sys.argv[1])
+    data = parse_jsonl(path)
+    if data is None:
+        raise SystemExit("No valid JSON found")
+    print(json.dumps(compute(data), indent=2, ensure_ascii=False))
+
+
+if __name__ == "__main__":
+    main()
--- a/experiments/dsv4_p800_max_context_length/parse_results.py
+++ b/experiments/dsv4_p800_max_context_length/parse_results.py
@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+"""Generate report.md from results.json for the max context length experiment.
+
+Usage:
+    python3 parse_results.py <result_root>
+"""
+import json
+import sys
+from pathlib import Path
+
+
+def main():
+    result_root = Path(sys.argv[1]) if len(sys.argv) > 1 else Path("results")
+    results_json = result_root / "results.json"
+    report_path = result_root / "report.md"
+
+    with open(results_json, "r", encoding="utf-8") as f:
+        data = json.load(f)
+
+    meta = data["metadata"]
+    cfg = data["config"]
+
+    with open(report_path, "w", encoding="utf-8") as f:
+        f.write("# P800 Max Context Length Exploration Report\n\n")
+        f.write(f"- Result root: `{result_root}`\n")
+        f.write(f"- Model: `{meta['model']}`\n")
+        f.write(f"- Hardware: {meta['hardware']}\n")
+        f.write(f"- TP: {cfg['tp']}, EP: {cfg['ep']}\n")
+        f.write(f"- Output len: {cfg['output_len']}, num prompts: {cfg['num_prompts']}, concurrency: {cfg['max_concurrency']}\n\n")
+
+        f.write("## Per-attempt results\n\n")
+        f.write("| Target len | Max context len | Status | TTFT mean(ms) | TTFT P95(ms) | E2E mean(ms) | E2E P99(ms) | Error |\n")
+        f.write("|---:|---:|---:|---:|---:|---:|---:|---:|\n")
+
+        max_supported = 0
+        for s in data.get("scenarios", []):
+            target = s["target_len"]
+            status = "✅ pass" if s["success"] else "❌ fail"
+            metrics = s.get("metrics") or {}
+            ttft = metrics.get("ttft_ms", {})
+            e2e = metrics.get("e2e_ms", {})
+            f.write(
+                f"| {target} | {s['max_context_len']} | {status} | "
+                f"{ttft.get('mean', 0):.2f} | {ttft.get('p95', 0):.2f} | "
+                f"{e2e.get('mean', 0):.2f} | {e2e.get('p99', 0):.2f} | "
+                f"{s.get('error', '') or ''} |\n"
+            )
+            if s["success"] and target > max_supported:
+                max_supported = target
+
+        f.write("\n## Maximum supported input length\n\n")
+        f.write(f"- **sglang-xpu**: {max_supported} tokens\n\n")
+
+    print(f"Wrote report to {report_path}")
+
+
+if __name__ == "__main__":
+    main()
--- a/experiments/dsv4_p800_max_context_length/results/20260709-032422/report.md
+++ b/experiments/dsv4_p800_max_context_length/results/20260709-032422/report.md
@ -0,0 +1,18 @@
+# P800 Max Context Length Exploration Report
+
+- Result root: `/data1/yy/sskj/experiments/dsv4_p800_max_context_length/results/20260709-032422`
+- Model: `/data1/models/DeepSeek-V4-Flash-INT8`
+- Hardware: 8x Kunlun P800 XPU
+- TP: 8, EP: 8
+- Output len: 1, num prompts: 1, concurrency: 1
+
+## Per-attempt results
+
+| Target len | Max context len | Status | TTFT mean(ms) | TTFT P95(ms) | E2E mean(ms) | E2E P99(ms) | Error |
+|---:|---:|---:|---:|---:|---:|---:|---:|
+| 4096 | 5120 | ✅ pass | 231.33 | 0.00 | 231.34 | 231.34 |  |
+
+## Maximum supported input length
+
+- **sglang-xpu**: 4096 tokens
+
--- a/experiments/dsv4_p800_max_context_length/results/20260709-032422/results.json
+++ b/experiments/dsv4_p800_max_context_length/results/20260709-032422/results.json
@ -0,0 +1,76 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_max_context_length",
+    "run_id": "20260709-032422",
+    "timestamp": "2026-07-09T03:24:22+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_max_context_length/run_bench.sh",
+    "env": "",
+    "git_commit": "1d1c79d",
+    "git_dirty": "dirty",
+    "description": "P800 max context length exploration for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {
+    "tp": 8,
+    "ep": 8,
+    "xpu_visible_devices": "0,1,2,3,4,5,6,7",
+    "output_len": 1,
+    "num_prompts": 1,
+    "max_concurrency": 1,
+    "request_rate": 10000,
+    "context_pad": 1024
+  },
+  "scenarios": [
+    {
+      "backend": "sglang",
+      "target_len": 4096,
+      "max_context_len": 5120,
+      "success": true,
+      "server_args": "python -m sglang.launch_server --host 0.0.0.0 --port 30013 --model-path /models --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --trust-remote-code --disable-custom-all-reduce --chunked-prefill-size 8192 --page-size 64 --mem-fraction-static 0.8 --max-prefill-tokens 5120 --max-running-requests 64 --tensor-parallel-size 8 --ep-size 8 --disable-shared-experts-fusion --quantization w8a8_int8 --kv-cache-dtype float16 --disable-piecewise-cuda-graph --cuda-graph-max-bs 32 --watchdog-timeout 3000000 --tool-call-parser deepseekv4 --reasoning-parser deepseek-v4 --speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --constrained-json-disable-any-whitespace --enable-metrics --enable-request-time-stats-logging --context-length 5120",
+      "metrics": {
+        "success_count": 1,
+        "total_count": 1,
+        "duration_s": 3.3442696970305406,
+        "request_throughput": 0.2990189460162034,
+        "input_token_throughput": 1224.781602882369,
+        "output_token_throughput": 0.2990189460162034,
+        "total_input_tokens": 4096,
+        "total_output_tokens": 1,
+        "e2e_ms": {
+          "mean": 231.34461202425882,
+          "p50": 231.34461202425882,
+          "p90": 231.34461202425882,
+          "p95": 0.0,
+          "p99": 231.34461202425882
+        },
+        "ttft_ms": {
+          "mean": 231.33470199536532,
+          "p50": 231.33470199536532,
+          "p90": 0.0,
+          "p95": 0.0,
+          "p99": 231.33470199536532
+        },
+        "tpot_ms": {
+          "mean": 0.0,
+          "p50": 0.0,
+          "p90": 0.0,
+          "p95": 0.0,
+          "p99": 0.0
+        },
+        "itl_ms": {
+          "mean": 0.0,
+          "p50": 0.0,
+          "p90": 0.0,
+          "p95": 0.0,
+          "p99": 0.0
+        }
+      },
+      "error": null
+    }
+  ]
+}
--- a/experiments/dsv4_p800_max_context_length/run_bench.sh
+++ b/experiments/dsv4_p800_max_context_length/run_bench.sh
@ -0,0 +1,245 @@
+#!/usr/bin/env bash
+# Max context length exploration for P800 SGLang INT8.
+set -Eeuo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"
+
+# shellcheck source=/dev/null
+source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+# shellcheck source=/dev/null
+source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+# shellcheck source=/dev/null
+source "${SCRIPT_DIR}/config.env"
+
+RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')}"
+RESULT_ROOT="${RESULT_ROOT:-${SCRIPT_DIR}/results/${RUN_ID}}"
+LOG_DIR="${RESULT_ROOT}/logs"
+RAW_DIR="${RESULT_ROOT}/raw_outputs"
+CONTAINER_NAME="${CONTAINER_NAME:-sglang-dsv4-flash}"
+CONTAINER_PYTHON="${CONTAINER_PYTHON:-/root/miniconda/envs/python310_torch25_cuda/bin/python}"
+
+ensure_result_root "$RESULT_ROOT"
+log_init "${LOG_DIR}/orchestrator.log"
+
+log "experiment=${EXPERIMENT_NAME}"
+log "run_id=${RUN_ID}"
+log "result_root=${RESULT_ROOT}"
+log "platform=${PLATFORM}"
+log "hardware=${HARDWARE}"
+log "model=${MODEL_PATH}"
+log "candidate_lengths=${CANDIDATE_LENS[*]}"
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+is_server_healthy() {
+  curl --fail --silent --show-error --max-time 5 "http://127.0.0.1:${PORT}/health" >/dev/null 2>&1
+}
+
+stop_server() {
+  log "stopping container ${CONTAINER_NAME}"
+  docker rm -f "$CONTAINER_NAME" 2>/dev/null || true
+  pkill -9 -f 'sglang.launch_server' 2>/dev/null || true
+  sleep 2
+}
+
+start_server() {
+  local target_len="$1"
+  log "starting server (target_len=${target_len})"
+  bash "${SCRIPT_DIR}/start_server.sh" "$target_len" >> "${LOG_DIR}/start_server_${target_len}.log" 2>&1
+}
+
+build_server_args() {
+  local target_len="$1"
+  local max_context_len=$(( target_len + CONTEXT_PAD ))
+  echo "python -m sglang.launch_server --host 0.0.0.0 --port ${PORT} --model-path /models --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --trust-remote-code --disable-custom-all-reduce --chunked-prefill-size 8192 --page-size 64 --mem-fraction-static 0.8 --max-prefill-tokens ${max_context_len} --max-running-requests 64 --tensor-parallel-size 8 --ep-size 8 --disable-shared-experts-fusion --quantization w8a8_int8 --kv-cache-dtype float16 --disable-piecewise-cuda-graph --cuda-graph-max-bs 32 --watchdog-timeout 3000000 --tool-call-parser deepseekv4 --reasoning-parser deepseek-v4 --speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --constrained-json-disable-any-whitespace --enable-metrics --enable-request-time-stats-logging --context-length ${max_context_len}"
+}
+
+append_scenario() {
+  local scenario_json="$1"
+  python3 - "$RESULT_JSON" "$scenario_json" <<'PY'
+import json
+import sys
+
+results_path, scenario_json = sys.argv[1], sys.argv[2]
+with open(results_path, "r", encoding="utf-8") as f:
+    data = json.load(f)
+
+data["scenarios"].append(json.loads(scenario_json))
+with open(results_path, "w", encoding="utf-8") as f:
+    json.dump(data, f, indent=2, ensure_ascii=False)
+PY
+}
+
+# Build a scenario JSON blob safely with Python.
+build_scenario_json() {
+  local target_len="$1"
+  local max_context_len="$2"
+  local success="$3"
+  local server_args="$4"
+  local error_msg="$5"
+  local metrics_json="${6:-null}"
+
+  python3 - "$target_len" "$max_context_len" "$success" "$server_args" "$error_msg" "$metrics_json" <<'PY'
+import json
+import sys
+
+target_len, max_context_len, success, server_args, error_msg, metrics_json = sys.argv[1:7]
+metrics = json.loads(metrics_json) if metrics_json not in ("null", "") else None
+print(json.dumps({
+    "backend": "sglang",
+    "target_len": int(target_len),
+    "max_context_len": int(max_context_len),
+    "success": success == "true",
+    "server_args": server_args,
+    "metrics": metrics,
+    "error": error_msg or None,
+}, ensure_ascii=False))
+PY
+}
+
+run_length() {
+  local target_len="$1"
+  local max_context_len=$(( target_len + CONTEXT_PAD ))
+  local output_file="${RAW_DIR}/sglang_ctx_${target_len}.jsonl"
+  local container_output="/tmp/bench_outputs/sglang_ctx_${target_len}.jsonl"
+  local detail_log="${LOG_DIR}/sglang_ctx_${target_len}.log"
+
+  log "trying sglang target_len=${target_len} (context-length=${max_context_len})"
+
+  stop_server
+  local server_args
+  server_args="$(build_server_args "$target_len")"
+  if ! start_server "$target_len"; then
+    local err="server failed to start"
+    log "ERROR: ${err}"
+    append_scenario "$(build_scenario_json "$target_len" "$max_context_len" "false" "$server_args" "$err")"
+    return 1
+  fi
+
+  docker exec "$CONTAINER_NAME" mkdir -p "$(dirname "$container_output")"
+
+  local bench_rc=0
+  docker exec "$CONTAINER_NAME" \
+    env HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_DATASETS_OFFLINE=1 \
+    "${CONTAINER_PYTHON}" -m sglang.bench_serving \
+      --backend sglang \
+      --host 127.0.0.1 \
+      --port "$PORT" \
+      --model "$MODEL_PATH" \
+      --dataset-name random \
+      --dataset-path /workspace/dummy_sharegpt.json \
+      --random-input-len "$target_len" \
+      --random-output-len "$OUTPUT_LEN" \
+      --random-range-ratio 1.0 \
+      --num-prompts "$NUM_PROMPTS" \
+      --max-concurrency "$MAX_CONCURRENCY" \
+      --request-rate "$REQUEST_RATE" \
+      --output-file "$container_output" \
+      --output-details \
+      > "$detail_log" 2>&1 || bench_rc=$?
+
+  if [[ "$bench_rc" -ne 0 ]]; then
+    local err="bench_serving exited with code ${bench_rc}; see ${detail_log}"
+    log "ERROR: sglang target_len=${target_len} failed; ${err}"
+    append_scenario "$(build_scenario_json "$target_len" "$max_context_len" "false" "$server_args" "$err")"
+    stop_server
+    return 1
+  fi
+
+  docker cp "${CONTAINER_NAME}:${container_output}" "$output_file" || {
+    local err="failed to copy output from container"
+    log "ERROR: ${err}"
+    append_scenario "$(build_scenario_json "$target_len" "$max_context_len" "false" "$server_args" "$err")"
+    stop_server
+    return 1
+  }
+
+  # Verify the request actually completed.
+  local completed
+  completed="$(python3 -c "
+import json
+with open('${output_file}') as f:
+    for line in f:
+        data = json.loads(line)
+        print(data.get('completed', 0))
+        break
+")"
+  if [[ "${completed:-0}" -lt "$NUM_PROMPTS" ]]; then
+    local err="only ${completed}/${NUM_PROMPTS} requests completed"
+    log "ERROR: sglang target_len=${target_len} ${err}"
+    append_scenario "$(build_scenario_json "$target_len" "$max_context_len" "false" "$server_args" "$err")"
+    stop_server
+    return 1
+  fi
+
+  local metrics_json
+  metrics_json="$(python3 "${SCRIPT_DIR}/extract_metrics.py" "$output_file")"
+
+  append_scenario "$(build_scenario_json "$target_len" "$max_context_len" "true" "$server_args" "" "$metrics_json")"
+
+  log "sglang target_len=${target_len} succeeded"
+  stop_server
+}
+
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+
+mkdir -p "$RAW_DIR" "$LOG_DIR"
+
+RESULT_JSON="${RESULT_ROOT}/results.json"
+write_metadata_json \
+  "$RESULT_JSON" \
+  "$EXPERIMENT_NAME" \
+  "$RUN_ID" \
+  "$MODEL_PATH" \
+  "sglang" \
+  "sglang-xpu" \
+  "$HARDWARE" \
+  "$ACCELERATOR" \
+  "$CHIP" \
+  "experiments/${EXPERIMENT_NAME}/run_bench.sh" \
+  "" \
+  "P800 max context length exploration for DeepSeek-V4-Flash-INT8"
+
+# Embed config.
+python3 - "$RESULT_JSON" <<'PY'
+import json
+import sys
+
+path = sys.argv[1]
+with open(path, "r", encoding="utf-8") as f:
+    data = json.load(f)
+
+data["config"] = {
+    "tp": 8,
+    "ep": 8,
+    "xpu_visible_devices": "0,1,2,3,4,5,6,7",
+    "output_len": 1,
+    "num_prompts": 1,
+    "max_concurrency": 1,
+    "request_rate": 10000,
+    "context_pad": 1024,
+}
+with open(path, "w", encoding="utf-8") as f:
+    json.dump(data, f, indent=2, ensure_ascii=False)
+PY
+
+stop_server
+
+for target_len in "${CANDIDATE_LENS[@]}"; do
+  if ! run_length "$target_len"; then
+    log "stopping exploration after first failure at target_len=${target_len}"
+    break
+  fi
+done
+
+log "parsing results"
+python3 "${SCRIPT_DIR}/parse_results.py" "$RESULT_ROOT" >> "${LOG_DIR}/parse.log" 2>&1 || {
+  log "WARNING: parse_results.py failed; see ${LOG_DIR}/parse.log"
+}
+
+log "all results saved to ${RESULT_ROOT}"
--- a/experiments/dsv4_p800_max_context_length/start_server.sh
+++ b/experiments/dsv4_p800_max_context_length/start_server.sh
@ -0,0 +1,133 @@
+#!/usr/bin/env bash
+# Start P800 SGLang INT8 server for a specific target context length.
+set -Eeuo pipefail
+
+TARGET_LEN="${1:-}"
+if [[ -z "$TARGET_LEN" ]]; then
+  echo "Usage: $0 <target_input_length_in_tokens>"
+  exit 1
+fi
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# shellcheck source=/dev/null
+source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
+# shellcheck source=/dev/null
+source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
+# shellcheck source=/dev/null
+source "${SCRIPT_DIR}/config.env"
+
+MAX_CONTEXT_LEN=$(( TARGET_LEN + CONTEXT_PAD ))
+CONTAINER_NAME="${CONTAINER_NAME:-sglang-dsv4-flash}"
+DOCKER_IMAGE="${DOCKER_IMAGE:-iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260511_4202}"
+PATCH_ROOT="${PATCH_ROOT:-${ROOT_DIR}/platforms/patches/kunlun_p800}"
+RESULT_ROOT="${RESULT_ROOT:-/tmp/${EXPERIMENT}}"
+SERVER_LOG="${RESULT_ROOT}/logs/server_${TARGET_LEN}.outer.log"
+
+mkdir -p "$(dirname "$SERVER_LOG")"
+
+log "starting P800 SGLang INT8 server (target_len=${TARGET_LEN}, context-length=${MAX_CONTEXT_LEN})"
+log "model: ${MODEL_PATH}"
+log "port: ${PORT}"
+log "server log: ${SERVER_LOG}"
+
+# Stop any existing container with the same name.
+docker rm -f "$CONTAINER_NAME" 2>/dev/null || true
+
+# Build device args.
+device_args=""
+for i in 0 1 2 3 4 5 6 7; do
+  device_args="${device_args} --device /dev/xpu${i}:/dev/xpu${i}"
+done
+device_args="${device_args} --device /dev/xpuctrl:/dev/xpuctrl"
+
+# Environment variables required by the P800 SGLang INT8 image.
+env_args=(
+  -e XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+  -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+  -e CUDA_DEVICE_ORDER=OAM_ID
+  -e SGLANG_USE_TRANSFORMERS_V5_TOKENIZER=1
+  -e XMLIR_FORCE_USE_XPU_GRAPH=1
+  -e SGLANG_DSV4_MODE=2604
+  -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+  -e SGLANG_NSA_DUAL_STREAM=true
+  -e SGLANG_NSA_QUANT_WQ_B_WK=false
+  -e SGLANG_FP8_PAGED_MQA_LOGITS_TORCH=1
+  -e SGLANG_OPT_DEEPGEMM_HC_PRENORM=false
+  -e SGLANG_OPT_USE_TILELANG_MHC_PRE=1
+  -e SGLANG_OPT_USE_TILELANG_MHC_POST=1
+  -e SGLANG_CLEAN_REQUEST_WHEN_RETRACT=1
+  -e SGLANG_SET_CPU_AFFINITY=1
+  -e SGLANG_OPT_USE_KLX_TOPK_KERNEL=1
+  -e XSGL_INTERTYPE_BFP16=1
+  -e ENABLE_FAST_BFP16_ATTN=1
+  -e XSGL_USE_DEEP_GEMM_BMM=1
+  -e XSGL_XDNN_QUANT=1
+  -e XSGL_FUSE_RMS_NORM_QUANT=1
+  -e XSGL_TRANSPOSE_MATMUL_WEIGHT=1
+  -e XINFER_QUANT_SDNN=1
+  -e XSGL_USE_MOE_SIGMOID_GROUP_TOPK_NORM=1
+  -e XSGL_EARLY_FIRST_TOKEN=1
+  -e XSGL_ENABLE_TGEMM_FP16=1
+  -e SGLANG_ENABLE_SPEC_V2=True
+  -e SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+  -e PYTHONDONTWRITEBYTECODE=1
+  -e XTORCH_OPS_LIB_DIR=/root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/xtorch_ops
+  -e XPU_RUNTIME_LIB_DIR=/root/miniconda/envs/python310_torch25_cuda/xcudart/lib
+  -e BKCL_TREE_THRESHOLD=1048576
+  -e CUDA_ENABLE_P2P_NO_UVA=1
+  -e NCCL_IB_GID_INDEX=3
+  -e IS_DSV4=1
+  -e MC_CUSTOM_TOPO_JSON=/workspace/nic_priority_matrix_test.json
+  # INT8 specific
+  -e SGLANG_DSV4_FP4_EXPERTS=false
+  -e SGLANG_APPLY_CONFIG_BACKUP=auto
+  -e BKCL_ENABLE_XDR=1
+  -e BKCL_RDMA_NICS=eth1,eth1,eth3,eth3,eth5,eth5,eth7,eth7
+  -e BKCL_RDMA_VERBS=1
+  -e XSGL_INT8_LM_HEAD=1
+  -e SGLANG_P800_ALL_GATHER_FALLBACK=0
+)
+
+# Launch args. Based on the proven P800 INT8 command from server_docker.sh,
+# but with dynamic --context-length and --max-prefill-tokens for the max-context
+# test. Keep --max-running-requests at 64 because setting it to 1 causes
+# req_to_token_pool allocation failures in this image.
+launch_args="--host 0.0.0.0 --port ${PORT} --model-path /models --attention-backend nsa --nsa-prefill klxdsa --nsa-decode klxdsa --trust-remote-code --disable-custom-all-reduce --chunked-prefill-size 8192 --page-size 64 --mem-fraction-static 0.8 --max-prefill-tokens ${MAX_CONTEXT_LEN} --max-running-requests 64 --tensor-parallel-size 8 --ep-size 8 --disable-shared-experts-fusion --quantization w8a8_int8 --kv-cache-dtype float16 --disable-piecewise-cuda-graph --cuda-graph-max-bs 32 --watchdog-timeout 3000000 --tool-call-parser deepseekv4 --reasoning-parser deepseek-v4 --speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --constrained-json-disable-any-whitespace --enable-metrics --enable-request-time-stats-logging --context-length ${MAX_CONTEXT_LEN}"
+
+# Base64-encode the bootstrap command to avoid host-shell quoting issues.
+server_cmd=$(cat <<EOF
+cd /workspace
+find /root/miniconda/envs/python310_torch25_cuda/lib/python3.10/site-packages/sglang -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true
+/root/miniconda/envs/python310_torch25_cuda/bin/pip install --upgrade safetensors -q
+/root/miniconda/envs/python310_torch25_cuda/bin/pip install https://files.pythonhosted.org/packages/14/8b/2a1333a6455c6fad401c2285dee6f58016c55b1cb44cae3a31f8a9cc7d83/apache_tvm_ffi-0.1.0b2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl -q
+/root/miniconda/envs/python310_torch25_cuda/bin/python -c "import torch; torch.float8_e8m0fnu = torch.uint8; import runpy, sys; sys.argv[0] = 'sglang.launch_server'; runpy.run_module('sglang.launch_server', run_name='__main__')" ${launch_args}
+EOF
+)
+server_cmd_b64=$(printf '%s' "$server_cmd" | base64 -w0)
+
+patch_mounts=(
+  -v "${PATCH_ROOT}/nic_priority_matrix_test.json:/workspace/nic_priority_matrix_test.json:ro"
+  -v "${PATCH_ROOT}/dummy_sharegpt.json:/workspace/dummy_sharegpt.json:ro"
+)
+
+docker run -d \
+  --name "${CONTAINER_NAME}" \
+  --privileged \
+  --network host \
+  --ipc host \
+  ${device_args} \
+  -v "${MODEL_PATH}:/models:ro" \
+  -v "${MODEL_PATH}:${MODEL_PATH}:ro" \
+  "${patch_mounts[@]}" \
+  "${env_args[@]}" \
+  "${DOCKER_IMAGE}" \
+  bash -c "echo '${server_cmd_b64}' | base64 -d | bash" \
+  >> "${SERVER_LOG}" 2>&1
+
+log "container ${CONTAINER_NAME} started, waiting for health"
+if health_check 127.0.0.1 "$PORT" 600; then
+  log "container ${CONTAINER_NAME} is healthy"
+else
+  log "ERROR: container ${CONTAINER_NAME} failed health check"
+  exit 1
+fi
--- a/experiments/dsv4_p800_sglang/results/20260708-043404/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-043404/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-043404",
+    "timestamp": "2026-07-08T04:34:04+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-043830/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-043830/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-043830",
+    "timestamp": "2026-07-08T04:38:30+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-044535/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-044535/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-044535",
+    "timestamp": "2026-07-08T04:45:35+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-045327/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-045327/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-045327",
+    "timestamp": "2026-07-08T04:53:27+00:00",
+    "model": "/data1/models/deepseek-ai/DeepSeek-V4-Flash",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-045554/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-045554/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-045554",
+    "timestamp": "2026-07-08T04:55:54+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-045616/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-045616/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-045616",
+    "timestamp": "2026-07-08T04:56:16+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-050025/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-050025/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-050025",
+    "timestamp": "2026-07-08T05:00:25+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-050713/report.md
+++ b/experiments/dsv4_p800_sglang/results/20260708-050713/report.md
@ -0,0 +1,16 @@
+# Benchmark Report: dsv4_p800_sglang
+
+## Metadata
+
+- **Run ID**: 20260708-050713
+- **Timestamp**: 2026-07-08T05:07:13+00:00
+- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800
+- **Engine/Backend**: sglang-xpu / sglang
+- **Hardware**: 8x Kunlun P800 XPU
+- **Model**: /data1/models/DeepSeek-V4-Flash-INT8
+- **Git Commit**: 2c332ff
+
+## Results
+
+| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
--- a/experiments/dsv4_p800_sglang/results/20260708-050713/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-050713/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-050713",
+    "timestamp": "2026-07-08T05:07:13+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-050722/report.md
+++ b/experiments/dsv4_p800_sglang/results/20260708-050722/report.md
@ -0,0 +1,16 @@
+# Benchmark Report: dsv4_p800_sglang
+
+## Metadata
+
+- **Run ID**: 20260708-050722
+- **Timestamp**: 2026-07-08T05:07:22+00:00
+- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800
+- **Engine/Backend**: sglang-xpu / sglang
+- **Hardware**: 8x Kunlun P800 XPU
+- **Model**: /data1/models/DeepSeek-V4-Flash-INT8
+- **Git Commit**: 2c332ff
+
+## Results
+
+| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
--- a/experiments/dsv4_p800_sglang/results/20260708-050722/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-050722/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-050722",
+    "timestamp": "2026-07-08T05:07:22+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-050858/report.md
+++ b/experiments/dsv4_p800_sglang/results/20260708-050858/report.md
@ -0,0 +1,16 @@
+# Benchmark Report: dsv4_p800_sglang
+
+## Metadata
+
+- **Run ID**: 20260708-050858
+- **Timestamp**: 2026-07-08T05:08:58+00:00
+- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800
+- **Engine/Backend**: sglang-xpu / sglang
+- **Hardware**: 8x Kunlun P800 XPU
+- **Model**: /data1/models/DeepSeek-V4-Flash-INT8
+- **Git Commit**: 2c332ff
+
+## Results
+
+| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
--- a/experiments/dsv4_p800_sglang/results/20260708-050858/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-050858/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-050858",
+    "timestamp": "2026-07-08T05:08:58+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-051023/report.md
+++ b/experiments/dsv4_p800_sglang/results/20260708-051023/report.md
@ -0,0 +1,16 @@
+# Benchmark Report: dsv4_p800_sglang
+
+## Metadata
+
+- **Run ID**: 20260708-051023
+- **Timestamp**: 2026-07-08T05:10:23+00:00
+- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800
+- **Engine/Backend**: sglang-xpu / sglang
+- **Hardware**: 8x Kunlun P800 XPU
+- **Model**: /data1/models/DeepSeek-V4-Flash-INT8
+- **Git Commit**: 2c332ff
+
+## Results
+
+| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
--- a/experiments/dsv4_p800_sglang/results/20260708-051023/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-051023/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-051023",
+    "timestamp": "2026-07-08T05:10:23+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-051200/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-051200/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-051200",
+    "timestamp": "2026-07-08T05:12:00+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "2c332ff",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-051316/report.md
+++ b/experiments/dsv4_p800_sglang/results/20260708-051316/report.md
@ -0,0 +1,17 @@
+# Benchmark Report: dsv4_p800_sglang
+
+## Metadata
+
+- **Run ID**: 20260708-051316
+- **Timestamp**: 2026-07-08T05:13:16+00:00
+- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800
+- **Engine/Backend**: sglang-xpu / sglang
+- **Hardware**: 8x Kunlun P800 XPU
+- **Model**: /data1/models/DeepSeek-V4-Flash-INT8
+- **Git Commit**: 2c332ff
+
+## Results
+
+| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
+| c32_i512_o256 | 32 | 512/256 | 10 | 0 | 1.87 | 262.65 | 506.4399079710711 | 507.2712521097855 | 21.948128755653826 | 29.154062995221466 | 5314.590020017349 |
--- a/experiments/dsv4_p800_sglang/results/20260708-051316/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-051316/results.json
--- a/experiments/dsv4_p800_sglang/results/20260708-052659/report.md
+++ b/experiments/dsv4_p800_sglang/results/20260708-052659/report.md
@ -0,0 +1,16 @@
+# Benchmark Report: dsv4_p800_sglang
+
+## Metadata
+
+- **Run ID**: 20260708-052659
+- **Timestamp**: 2026-07-08T05:26:59+00:00
+- **Chip/Accelerator**: Kunlun P800 XPU / kunlun_p800
+- **Engine/Backend**: sglang-xpu / sglang
+- **Hardware**: 8x Kunlun P800 XPU
+- **Model**: /data1/models/DeepSeek-V4-Flash-INT8
+- **Git Commit**: 4ef6543
+
+## Results
+
+| Scenario | Conc | In/Out | Success | Failed | Req/s | OutTok/s | TTFT p50 | TTFT p99 | TPOT p50 | TPOT p99 | E2E p99 |
+|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
--- a/experiments/dsv4_p800_sglang/results/20260708-052659/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-052659/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-052659",
+    "timestamp": "2026-07-08T05:26:59+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "4ef6543",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}
--- a/experiments/dsv4_p800_sglang/results/20260708-054332/results.json
+++ b/experiments/dsv4_p800_sglang/results/20260708-054332/results.json
@ -0,0 +1,20 @@
+{
+  "metadata": {
+    "experiment": "dsv4_p800_sglang",
+    "run_id": "20260708-054332",
+    "timestamp": "2026-07-08T05:43:32+00:00",
+    "model": "/data1/models/DeepSeek-V4-Flash-INT8",
+    "backend": "sglang",
+    "engine": "sglang-xpu",
+    "hardware": "8x Kunlun P800 XPU",
+    "accelerator": "Kunlun P800 XPU",
+    "chip": "kunlun_p800",
+    "script": "experiments/dsv4_p800_sglang/run_bench.sh",
+    "env": "",
+    "git_commit": "4ef6543",
+    "git_dirty": "dirty",
+    "description": "Kunlun P800 SGLang benchmark for DeepSeek-V4-Flash-INT8"
+  },
+  "config": {},
+  "scenarios": []
+}