Stage
Disqualified
11 of 12 stages
Settled in
7h 27m
committed Oct 10, 13:44 UTC
Round score
—
awaiting round
p99 latency
—
ceiling 2000 / 50 ms
Round 14: disqualified · no score
11/12 stages
Intake & gates
6/6Patch hash recorded; awaiting fetch.
{
"hotkey": "5D7K68fzPZUH4Jhr554FXJW2KwX8FAzGLP6HQpwfPEBodYJg",
"payment_tx": 17,
"commit_block": 9253103,
"payment_block": 9253100,
"patch_fingerprint": "sha256:f09d9d3ebdcc5f2093b89f38797af056fa461605f69ba95b843ffe8beba60a7f"
}A worker claimed the submission and started the pipeline.
{
"job_id": 232
}Patch artifact retrieved from object storage.
{
"size": 150813,
"patch_hash": "sha256:7a62232851c7cb2726c880e24d2c19c9c4bb633075d5eeeb0e1750a5efcde686"
}Integrity and path constraints checked.
{
"identity": "ok",
"patch_hash": "sha256:7a62232851c7cb2726c880e24d2c19c9c4bb633075d5eeeb0e1750a5efcde686"
}Patch applied onto the baseline checkout.
{
"ok": true
}Public API / surface compatibility held.
{
"files": [
"python/sglang/kernels/jit/csrc/gemm/fp8_blockwise/fp8_blockwise_scaled_mm_entry.cuh",
"python/sglang/kernels/jit/csrc/gemm/fp8_blockwise/fp8_blockwise_scaled_mm_sm120.cuh",
"python/sglang/kernels/ops/activation/silu_mul_quant.py",
"python/sglang/kernels/ops/attention/fla/layernorm_gated.py",
"python/sglang/kernels/ops/gemm/fp8_blockwise_gemm.py",
"python/sglang/kernels/ops/layernorm/fused_add_rmsnorm_quant.py",
"python/sglang/kernels/ops/speculative/__init__.py",
"python/sglang/kernels/ops/speculative/cache_locs.py",
"python/sglang/kernels/ops/speculative/reject_sampling.py",
"python/sglang/kernels/ops/speculative/softmax.py",
"python/sglang/srt/arg_groups/attention_hook.py",
"python/sglang/srt/arg_groups/fields/spec.py",
"python/sglang/srt/arg_groups/speculative_hook.py",
"python/sglang/srt/environ.py",
"python/sglang/srt/layers/attention/flashinfer_backend.py",
"python/sglang/srt/layers/attention/linear/gdn_backend.py",
"python/sglang/srt/layers/layernorm.py",
"python/sglang/srt/layers/logits_processor.py",
"python/sglang/srt/layers/quantization/fp8.py",
"python/sglang/srt/layers/quantization/fp8_utils.py",
"python/sglang/srt/layers/quantization/sm120_nvfp4_decode.py",
"python/sglang/srt/managers/scheduler_components/batch_result_processor.py",
"python/sglang/srt/mem_cache/memory_pool.py",
"python/sglang/srt/model_executor/forward_batch_info.py",
"python/sglang/srt/model_executor/runner/decode_cuda_graph_runner.py",
"python/sglang/srt/models/qwen2_moe.py",
"python/sglang/srt/models/qwen3_5.py",
"python/sglang/srt/models/qwen3_5_mtp.py",
"python/sglang/srt/speculative/adaptive_cost_policy.py",
"python/sglang/srt/speculative/adaptive_runtime_state.py",
"python/sglang/srt/speculative/adaptive_spec_params.py",
"python/sglang/srt/speculative/base_spec_worker.py",
"python/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py",
"python/sglang/srt/speculative/eagle_info.py",
"python/sglang/srt/speculative/eagle_utils.py",
"python/sglang/srt/speculative/eagle_worker_common.py",
"python/sglang/srt/speculative/eagle_worker_v2.py",
"python/sglang/srt/speculative/ngram_worker.py",
"python/sglang/srt/speculative/spec_utils.py"
]
}Build
3/3Hermetic engine image build in progress.
No structured detail recorded for this step.
Candidate engine image pushed to the registry.
{
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:6ff147fa9ab03f19deb85be556c49dbe146156b78e02d9464296cc5d67658680",
"image_digest": "sha256:6ff147fa9ab03f19deb85be556c49dbe146156b78e02d9464296cc5d67658680"
}Candidate engine image built and digest pinned.
{
"mock": false,
"build_log": "/var/log/pareton/builds/95a8534c-2061-443e-ae3d-5be4b6ca2231/build.log",
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:6ff147fa9ab03f19deb85be556c49dbe146156b78e02d9464296cc5d67658680",
"image_tag": "ghcr.io/pareton-ai/pareton-engine:7a62232851c7cb2726c880e24d2c19c9c4bb633075d5eeeb0e1750a5efcde686"
}Round
2/3Waiting to be seated in a round.
No structured detail recorded for this step.
Seated in a round; waiting to run or running.
{
"ordinal": 14,
"round_id": "e33f41ff-db3e-4fbb-9a8c-c44f699eae1a"
}Other events
The image ran and produced wrong output.
{
"score": null,
"reason": "engine died before becoming healthy (last error: [Errno 111] Connection refused); container log tail:\n/src/python/sglang/launch_server.py:63: UserWarning: 'python -m sglang.launch_server' is still supported, but 'sglang serve' is the recommended entrypoint.\n Example: sglang serve --model-path <model> [options]\n warnings.warn(\n[2026-10-10 21:07:55] Attention backend not specified. Use flashinfer backend by default.\n[2026-10-10 21:07:55] Qwen3.5 GDN EAGLE topk=1 on SM120: defaulting to --enable-linear-replayssm-spec.\n[2026-10-10 21:07:55] Qwen3.5 GDN EAGLE topk=1 on SM120: defaulting to fp8_e4m3 KV.\n[2026-10-10 21:07:55] --enable-linear-replayssm-spec: setting --mamba-ssm-dtype float32 (cached replay uses compensated checkpoint projection and materialization).\n[2026-10-10 21:07:55] --mm-enable-dp-encoder is enabled with TP=1, so the encoder has no data-parallel work to distribute. Disable it unless you need to validate this configuration.\n[2026-10-10 21:07:55] Qwen3.5 GDN EAGLE topk=1 on SM120: defaulting to cost-aware adaptive draft depth [2, 3, 4, 5, 6, 7].\n[2026-10-10 21:07:55] Adaptive spec up to 8 draft tokens: GDN ReplaySSM ring 32 -> 32.\n[2026-10-10 21:07:55] Rejection sampling is enabled for speculative decoding (speculative_use_rejection_sampling=True).\n[2026-10-10 21:07:57] kill_process_tree called: parent_pid=1, include_parent=False, pid=1\nTraceback (most recent call last):\n File \"<frozen runpy>\", line 198, in _run_module_as_main\n File \"<frozen runpy>\", line 88, in _run_code\n File \"/src/python/sglang/launch_server.py\", line 76, in <module>\n run_server(server_args)\n File \"/src/python/sglang/launch_server.py\", line 59, in run_server\n launch_server(server_args)\n File \"/src/python/sglang/srt/entrypoints/http_server.py\", line 2825, in launch_server\n ) = Engine._launch_subprocesses(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/src/python/sglang/srt/entrypoints/engine.py\", line 1098, in _launch_subprocesses\n publish(server_args, role=\"tokenizer\")\n File \"/src/python/sglang/srt/runtime_context.py\", line 1587, in publish\n _CONTEXT.set_server_args(server_args)\n File \"/src/python/sglang/srt/runtime_context.py\", line 1061, in set_server_args\n max_draft_tokens_of(server_args),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/src/python/sglang/srt/arg_groups/overrides.py\", line 1968, in max_speculative_num_draft_tokens\n raise ValueError(\nValueError: The speculative algorithm declared max_speculative_num_draft_tokens=8, below the configured speculative_num_draft_tokens=9.\n",
"ordinal": 14,
"round_id": "e33f41ff-db3e-4fbb-9a8c-c44f699eae1a"
}