kimbochen · Oct 19, 2026 · Oct 19, 2026 · Nov 1, 2026 · Nov 1, 2026 · Nov 1, 2026
@@ -0,0 +1,319 @@
+#!/usr/bin/env bash
+
+# MiMo-V2.6-Flash B300 vLLM SPEED-Bench AL matrix collector for the checkpoint's DFlash drafter.
+#
+# For each thinking mode (on/off) and DFlash draft length (num_speculative_tokens), measure
+# the REAL acceptance length (AL) on one SPEED-Bench category and emit a YAML matrix in the
+# golden_al_distribution shape.
+#
+# The drafter is the BF16 dflash/ subfolder of the target checkpoint, served as shipped. Its
+# block size of 8 bounds the draft length at 7. Thinking is ON by default in MiMo's chat
+# template, so the OFF cell MUST pass enable_thinking:false and the ON cell enable_thinking:true.
+#
+# AL is 1 + delta(accepted draft tokens) / delta(verification drafts) from vLLM's spec-decode
+# counters around each SPEED-Bench pass.
+#
+# Dispatch this collector through speedbench-al.yml with framework=vllm.
+
+set -o pipefail
+repo_root="$(cd "$(dirname "$0")/../../.." && pwd)"
+source "$repo_root/benchmarks/check_env.sh"
+check_env_vars \
+    CATEGORY CHAT_TEMPLATE_KWARGS_ON MODEL MODEL_PATH MTP_LIST OUT_YAML PORT \
+    SPEEDBENCH_OUTPUT_LEN THINKING_MODES
+
+if ! python3 -c 'import json, sys; sys.exit(json.loads(sys.argv[1]).get("enable_thinking") is not True)' \
+        "$CHAT_TEMPLATE_KWARGS_ON"; then
+    echo "CRITICAL: dispatch with thinking-kwargs='{\"enable_thinking\": true}' (got '$CHAT_TEMPLATE_KWARGS_ON')"
+    exit 1
+fi
+
+SERVE_MODEL="${MODEL_PATH}"
+DRAFT_MODEL_PATH="$MODEL_PATH/dflash"
+MODEL_KEY="$(basename "$SERVE_MODEL" | tr '[:upper:]' '[:lower:]')"
+# AL is a per-draft accept/reject property independent of batch size, so batch the
+# SPEED-Bench pass to cut wall-clock.
+CONCURRENCY="32"
+TEMPERATURE="1.0"
+TOP_P="0.95"
+CHAT_TEMPLATE_KWARGS_OFF='{"enable_thinking": false}'
+
+SPEEDBENCH_DIR="/workspace/speed_bench_data"
+RESULTS_DIR="/workspace/speedbench_results"
+
+export VLLM_ENGINE_READY_TIMEOUT_S=3600
+
+mkdir -p "$RESULTS_DIR"
+
+# `vllm bench serve` os.execv's the CLIENT into the Rust vllm-rs binary whenever the
+# dataset (speed_bench qualifies) and backend are supported, with no opt-out. The
+# Rust flag surface lacks --speed-bench-output-len, --save-detailed and
+# --chat-template-kwargs, so every cell would die at argument parsing. Call the
+# Python entrypoint directly (vllm.benchmarks.serve.main), as the CLI's own Python
+# fallback does. The SERVER keeps the Rust frontend; AL is read from /metrics.
+BENCH_DRIVER="$RESULTS_DIR/bench_serve_python.py"
+cat > "$BENCH_DRIVER" <<'PYEOF'
+# Python-only `vllm bench serve`: bypasses the Rust os.execv delegation in
+# vllm/entrypoints/cli/benchmark/serve.py by importing the benchmark directly.
+from vllm.benchmarks.serve import add_cli_args, main
+
+try:  # import path moved in newer vLLM
+    from vllm.utils.argparse_utils import FlexibleArgumentParser
+except ImportError:
+    from vllm.utils import FlexibleArgumentParser
+
+parser = FlexibleArgumentParser(
+    description="vllm bench serve (Python entrypoint, no Rust delegation)"
+)
+add_cli_args(parser)
+main(parser.parse_args())
+PYEOF
+if [[ ! -s "$BENCH_DRIVER" ]]; then
+    echo "CRITICAL: could not write the benchmark driver to $BENCH_DRIVER — aborting."
+    exit 1
+fi
+
+nvidia-smi
+GPU_NAME="$(nvidia-smi --query-gpu=name --format=csv,noheader | head -1)"
+
+if [[ ! -d "$MODEL_PATH" || -z "$(ls -A "$MODEL_PATH" 2>/dev/null)" ]]; then
+    if [[ ! -w "$(dirname "$MODEL_PATH")" ]]; then
+        echo "CRITICAL: $MODEL_PATH is empty and $(dirname "$MODEL_PATH") is not writable."
+        echo "The cluster's models.entries names this checkpoint but the weights were never staged."
+        exit 1
+    fi
+    echo "=== $MODEL_PATH is empty; downloading $MODEL (first run only) ==="
+    hf download "$MODEL" --local-dir "$MODEL_PATH"
+fi
+if [[ ! -f "$DRAFT_MODEL_PATH/config.json" ]]; then
+    echo "CRITICAL: no DFlash drafter at $DRAFT_MODEL_PATH"
+    exit 1
+fi
+
+DRAFT_BLOCK=$(python3 -c '
+import json, sys
+print(json.load(open(sys.argv[1]))["block_size"])
+' "$DRAFT_MODEL_PATH/config.json")
+for mtp in $MTP_LIST; do
+    if [[ "$mtp" -lt 1 || "$mtp" -ge "$DRAFT_BLOCK" ]]; then
+        echo "CRITICAL: DFlash draft length $mtp is outside 1..$((DRAFT_BLOCK - 1)) (block_size $DRAFT_BLOCK)"
+        exit 1
+    fi
+done
+
+echo "=== Downloading SPEED-Bench dataset ==="
+pip install -q datasets tiktoken
+curl -LsSf https://raw.githubusercontent.com/NVIDIA-NeMo/Skills/refs/heads/main/nemo_skills/dataset/speed-bench/prepare.py \
+  | python3 - --config qualitative --output_dir "$SPEEDBENCH_DIR"
+
+if [[ ! -f "$SPEEDBENCH_DIR/qualitative.jsonl" ]]; then
+    echo "CRITICAL: SPEED-Bench download failed — $SPEEDBENCH_DIR/qualitative.jsonl not found"
+    exit 1
+fi
+
+# Preflight the client flags every cell uses; otherwise a CLI mismatch only shows up
+# as an all-N/A matrix after every server start. --help=all prints every flag group.
+BENCH_HELP="$(python3 "$BENCH_DRIVER" --help=all 2>&1)"
+for flag in --speed-bench-category --speed-bench-output-len --chat-template-kwargs --save-detailed; do
+    if [[ "$BENCH_HELP" != *"$flag"* ]]; then
+        echo "CRITICAL: the Python benchmark entrypoint does not support $flag — aborting."
+        echo "--- python3 $BENCH_DRIVER --help=all ---"
+        echo "$BENCH_HELP"
+        exit 1
+    fi
+done
+echo "=== Benchmark client flag preflight OK ==="
+
+# Containers share the node's network namespace, so a process left on the node outside
+# Slurm can hold $PORT and every cell then dies with "Address already in use". Report
+# the holder and serve on a free port instead.
+port_in_use() {
+    python3 -c '
+import socket, sys
+s = socket.socket()
+try:
+    s.bind(("0.0.0.0", int(sys.argv[1])))
+except OSError:
+    sys.exit(0)
+sys.exit(1)
+' "$1"
+}
+if port_in_use "$PORT"; then
+    echo "WARNING: port $PORT is already in use on $(hostname); holder:"
+    (ss -ltnp 2>/dev/null || netstat -ltnp 2>/dev/null) | grep -E ":$PORT\b" || echo "  (ss/netstat unavailable)"
+    PORT=$(python3 -c 'import socket; s = socket.socket(); s.bind(("0.0.0.0", 0)); print(s.getsockname()[1])')
+    echo "Serving on free port $PORT instead."
+fi
+
+fetch_metric() {
+    local port="$1" name="$2"
+    curl -s "http://localhost:${port}/metrics" \
+      | grep -oP "${name}\\{[^}]*\\} \\K[0-9.]+" || echo "0"
+}
+
+SERVER_PID=""
+_descendants() {
+    local pid="$1" child
+    for child in $(pgrep -P "$pid" 2>/dev/null || true); do
+        echo "$child"
+        _descendants "$child"
+    done
+}
+cleanup_server() {
+    if [[ -n "$SERVER_PID" ]]; then
+        local descendants
+        descendants=$(_descendants "$SERVER_PID")
+        kill "$SERVER_PID" 2>/dev/null || true
+        wait "$SERVER_PID" 2>/dev/null || true
+        local pid
+        for pid in $descendants; do
+            kill -9 "$pid" 2>/dev/null || true
+        done
+        local waited=0
+        while [[ $waited -lt 120 ]]; do
+            local used
+            used=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits 2>/dev/null | sort -rn | head -1)
+            if [[ -z "$used" || "$used" -lt 2000 ]]; then break; fi
+            sleep 3; waited=$((waited + 3))
+        done
+        SERVER_PID=""
+    fi
+}
+trap 'cleanup_server' EXIT
+
+declare -A AL_RESULT
+
+run_cell() {
+    local mode="$1" mtp="$2"
+    local think_args=(--chat-template-kwargs "$CHAT_TEMPLATE_KWARGS_OFF")
+    if [[ "$mode" == "on" ]]; then
+        think_args=(--chat-template-kwargs "$CHAT_TEMPLATE_KWARGS_ON")
+    fi
+
+    echo ""
+    echo "=========================================="
+    echo "  Cell: thinking=$mode  DFLASH=$mtp  category=$CATEGORY"
+    echo "=========================================="
+
+    local serve_args=(
+        --host 0.0.0.0 --port "$PORT"
+        --tensor-parallel-size 4
+        --trust-remote-code
+        --no-enable-prefix-caching
+        --gpu-memory-utilization 0.9
+        --max-model-len 32768
+        --reasoning-parser mimo
+        --tool-call-parser mimo
+        --enable-auto-tool-choice
+        --speculative-config "{\"method\": \"dflash\", \"model\": \"$DRAFT_MODEL_PATH\", \"num_speculative_tokens\": $mtp}"
+        --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}'
+    )
+
+    local server_log="$RESULTS_DIR/server_${mode}_mtp${mtp}.log"
+    vllm serve "$SERVE_MODEL" "${serve_args[@]}" > "$server_log" 2>&1 &
+    SERVER_PID=$!
+
+    if ! PYTHONSAFEPATH=1 PYTHONPATH="$repo_root${PYTHONPATH:+:$PYTHONPATH}" python3 -m infx.bench wait \
+            --url "http://0.0.0.0:${PORT}/health" --pid "$SERVER_PID" --log "$server_log"; then
+        echo "  -> server failed to start (thinking=$mode dflash=$mtp), recording N/A"
+        AL_RESULT["${mode}_${mtp}"]="N/A"
+        cleanup_server
+        return
+    fi
+
+    local acc_before drf_before acc_after drf_after
+    acc_before=$(fetch_metric "$PORT" "vllm:spec_decode_num_accepted_tokens_total")
+    drf_before=$(fetch_metric "$PORT" "vllm:spec_decode_num_drafts_total")
+
+    python3 "$BENCH_DRIVER" \
+        --model "$SERVE_MODEL" \
+        --port "$PORT" \
+        --dataset-name speed_bench \
+        --dataset-path "$SPEEDBENCH_DIR" \
+        --speed-bench-category "$CATEGORY" \
+        --speed-bench-output-len "$SPEEDBENCH_OUTPUT_LEN" \
+        --num-prompts -1 \
+        --max-concurrency "$CONCURRENCY" \
+        --save-result \
+        --save-detailed \
+        --result-dir "$RESULTS_DIR" \
+        --result-filename "speedbench_${mode}_mtp${mtp}" \
+        --trust-remote-code \
+        --temperature "$TEMPERATURE" \
+        --top-p "$TOP_P" \
+        "${think_args[@]}"
+    local bench_rc=$?
+    if [[ $bench_rc -ne 0 ]]; then
+        echo "  -> benchmark client exited rc=$bench_rc (thinking=$mode dflash=$mtp)"
+    fi
+
+    acc_after=$(fetch_metric "$PORT" "vllm:spec_decode_num_accepted_tokens_total")
+    drf_after=$(fetch_metric "$PORT" "vllm:spec_decode_num_drafts_total")
+
+    local delta_acc delta_drf al
+    delta_acc=$(awk "BEGIN {printf \"%d\", $acc_after - $acc_before}")
+    delta_drf=$(awk "BEGIN {printf \"%d\", $drf_after - $drf_before}")
+    if [[ "$delta_drf" -gt 0 ]]; then
+        al=$(awk "BEGIN {printf \"%.2f\", 1 + ($delta_acc / $delta_drf)}")
+    else
+        al="N/A"
+    fi
+    echo "  -> thinking=$mode DFLASH=$mtp AL=$al (accepted=$delta_acc drafts=$delta_drf)"
+    AL_RESULT["${mode}_${mtp}"]="$al"
+
+    cleanup_server
+}
+
+for mode in $THINKING_MODES; do
+    for mtp in $MTP_LIST; do
+        run_cell "$mode" "$mtp"
+    done
+done
+
+emit_mode_block() {
+    local mode="$1"
+    for mtp in $MTP_LIST; do
+        echo "    $mtp: ${AL_RESULT[${mode}_${mtp}]:-N/A}"
+    done
+}
+
+{
+    echo "# Acceptance Length (AL) reference values measured with SPEED-Bench."
+    echo "# dataset: $CATEGORY | temperature: $TEMPERATURE | top_p: $TOP_P | output_len: $SPEEDBENCH_OUTPUT_LEN"
+    echo "# thinking_on chat_template_kwargs: $CHAT_TEMPLATE_KWARGS_ON"
+    echo "# thinking_off chat_template_kwargs: $CHAT_TEMPLATE_KWARGS_OFF"
+    echo "# draft: $MODEL/dflash (BF16, greedy drafting)"
+    echo "# Measured on $MODEL_KEY ($GPU_NAME, vLLM DFlash), per num_speculative_tokens."
+    echo "# Auto-generated by benchmarks/single_node/speedbench/mimov2.6flash_fp4_b300_vllm.sh (speedbench-al.yml)."
+    echo "#"
+    echo "# key = num_speculative_tokens (DFlash draft tokens); value = golden AL"
+    echo "${MODEL_KEY}:"
+    if [[ " $THINKING_MODES " == *" on "* ]]; then
+        echo "  thinking_on:"
+        emit_mode_block on
+    fi
+    if [[ " $THINKING_MODES " == *" off "* ]]; then
+        echo "  thinking_off:"
+        emit_mode_block off
+    fi
+} > "$OUT_YAML"
+
+echo ""
+echo "=========================================="
+echo "  SPEED-Bench AL matrix written to: $OUT_YAML"
+echo "=========================================="
+cat "$OUT_YAML"
+
+# A matrix where every cell is N/A is a failed collection, not a result: fail the
+# job so it is not mistaken for a curve worth reviewing.
+MEASURED=0
+for mode in $THINKING_MODES; do
+    for mtp in $MTP_LIST; do
+        [[ "${AL_RESULT[${mode}_${mtp}]:-N/A}" != "N/A" ]] && MEASURED=$((MEASURED + 1))
+    done
+done
+if [[ "$MEASURED" -eq 0 ]]; then
+    echo "CRITICAL: no cell produced an AL value — see the server logs and the"
+    echo "benchmark client output above."
+    exit 1
+fi
@@ -146,6 +146,7 @@ Before accepting an updated curve, reviewers should verify:
 | GLM-5.3 | MTP (provisional, K=3 copied from GLM-5.2) | [`glm5.3_mtp.yaml`](glm5.3_mtp.yaml) | [28058352479](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/28058352479) (GLM-5.2) |
 | Qwen3.8-Flash-Next | MTP (native) | [`qwen3.8next_mtp.yaml`](qwen3.8next_mtp.yaml) | [33034290269](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/33034290269) |
 | Muse Spark Open | DFlash2 | [`musespark_dflash.yaml`](musespark_dflash.yaml) | [38808046215](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/38808046215) |
+| MiMo-V2.6-Flash | DFlash | [`mimov2.6flash_dflash.yaml`](mimov2.6flash_dflash.yaml) | [41346734342](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/41346734342) |
 
 ## Using golden curves in srt-slurm runs
 

@@ -139,6 +139,7 @@ gh workflow run speedbench-al.yml \
 | GLM-5.3 | MTP（临时，K=3 取自 GLM-5.2） | [`glm5.3_mtp.yaml`](glm5.3_mtp.yaml) | [28058352479](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/28058352479)（GLM-5.2） |
 | Qwen3.8-Flash-Next | MTP (native) | [`qwen3.8next_mtp.yaml`](qwen3.8next_mtp.yaml) | [33034290269](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/33034290269) |
 | Muse Spark Open | DFlash2 | [`musespark_dflash.yaml`](musespark_dflash.yaml) | [38808046215](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/38808046215) |
+| MiMo-V2.6-Flash | DFlash | [`mimov2.6flash_dflash.yaml`](mimov2.6flash_dflash.yaml) | [41346734342](https://github.com/SemiAnalysisAI/InferenceX/actions/runs/41346734342) |
 
 ## 在 srt-slurm 运行中使用黄金曲线
 

@@ -0,0 +1,27 @@
+# Source GitHub Actions run: https://github.com/SemiAnalysisAI/InferenceX/actions/runs/41346734342
+# Acceptance Length (AL) reference values measured with SPEED-Bench.
+# dataset: coding | temperature: 1.0 | top_p: 0.95 | output_len: 4096
+# thinking_on chat_template_kwargs: {"enable_thinking": true}
+# thinking_off chat_template_kwargs: {"enable_thinking": false}
+# draft: XiaomiMiMo/MiMo-V2.6-Flash-RL/dflash (BF16, greedy drafting)
+# Measured on mimo-v2.6-flash-rl (NVIDIA B300 SXM6 AC, vLLM DFlash), per num_speculative_tokens.
+# Auto-generated by benchmarks/single_node/speedbench/mimov2.6flash_fp4_b300_vllm.sh (speedbench-al.yml).
+#
+# key = num_speculative_tokens (DFlash draft tokens); value = golden AL
+mimo-v2.6-flash-rl:
+  thinking_on:
+    1: 1.84
+    2: 2.51
+    3: 2.97
+    4: 3.35
+    5: 3.76
+    6: 3.86
+    7: 4.08
+  thinking_off:
+    1: 1.83
+    2: 2.52
+    3: 2.95
+    4: 3.30
+    5: 3.74
+    6: 3.89
+    7: 4.00
@@ -39,6 +39,7 @@ def test_every_committed_curve_is_valid() -> None:
         ("dsv4dsparkprob", {"method": "dspark"}, "dsv4-pro-0813-dspark"),
         ("dsv41flash", {"method": "dspark"}, "dsv41flash_dspark"),
         ("musespark", {"method": "dflash"}, "musespark_dflash"),
+        ("mimov2.6flash", {"method": "dflash"}, "mimov2.6flash_dflash"),
         ("minimaxm31flash", {"method": "dspark"}, "minimaxm31flash_dspark"),
         ("kimik3", {"method": "dspark", "draft_sample_method": "greedy"}, "kimik3_dspark"),
         (