Entries
3
2 scored · 1 disqualified
Settled in
1h 15m
seated Oct 10, 19:56 UTC
Top score
—
no scored challenger
Leader
Held
incumbent kept the lead
3
| Role | Miner | Patch | Status | Score | Duration | Open |
|---|---|---|---|---|---|---|
| baseline | — | — | scored | 0 score breakdown | — | |
| leader |
| 262598c…14196 |
| scored |
| 0.6521 score breakdown |
| — |
| challenger | 7a62232…de686 | disqualifiedengine died before becoming healthy (last error: [Errno 111] Connection refused); container log tail: /src/python/sglang/launch server.py:63: UserWarning: 'python -m sglang.launch server' is still supported, but 'sglang serve' is the recommended entrypoint. Example: sglang serve --model-path <model> [options] warnings.warn( [2026-10-10 21:07:55] Attention backend not specified. Use flashinfer backend by default. [2026-10-10 21:07:55] Qwen3.5 GDN EAGLE topk=1 on SM120: defaulting to --enable-linear-replayssm-spec. [2026-10-10 21:07:55] Qwen3.5 GDN EAGLE topk=1 on SM120: defaulting to fp8 e4m3 KV. [2026-10-10 21:07:55] --enable-linear-replayssm-spec: setting --mamba-ssm-dtype float32 (cached replay uses compensated checkpoint projection and materialization). [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. [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]. [2026-10-10 21:07:55] Adaptive spec up to 8 draft tokens: GDN ReplaySSM ring 32 -> 32. [2026-10-10 21:07:55] Rejection sampling is enabled for speculative decoding (speculative use rejection sampling=True). [2026-10-10 21:07:57] kill process tree called: parent pid=1, include parent=False, pid=1 Traceback (most recent call last): File "<frozen runpy>", line 198, in run module as main File "<frozen runpy>", line 88, in run code File "/src/python/sglang/launch server.py", line 76, in <module> run server(server args) File "/src/python/sglang/launch server.py", line 59, in run server launch server(server args) File "/src/python/sglang/srt/entrypoints/http server.py", line 2825, in launch server ) = Engine. launch subprocesses( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/src/python/sglang/srt/entrypoints/engine.py", line 1098, in launch subprocesses publish(server args, role="tokenizer") File "/src/python/sglang/srt/runtime context.py", line 1587, in publish CONTEXT.set server args(server args) File "/src/python/sglang/srt/runtime context.py", line 1061, in set server args max draft tokens of(server args), ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/src/python/sglang/srt/arg groups/overrides.py", line 1968, in max speculative num draft tokens raise ValueError( ValueError: The speculative algorithm declared max speculative num draft tokens=8, below the configured speculative num draft tokens=9. | — score breakdown | — |
15/15 steps
Setup
4/4Waiting on a provider to hand over a machine.
Installing the harness and shipping the repo.
Fetching the baseline and candidate engine images.
Staging the campaign model onto the pod.
Baseline
2/2Loading weights and waiting for the server to answer.
Second baseline
2/2Loading weights and waiting for the server to answer.
Incumbent
2/2Loading weights and waiting for the server to answer.
Candidate 1 of 1
2/2Loading weights and waiting for the server to answer.
Scorer
2/2Loading weights and waiting for the server to answer.
Teardown
1/1Destroying the pod and its volume.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
The pinned baseline image teacher-forces captured outputs against the campaign thresholds.