Entries
5
4 scored · 1 disqualified
Settled in
1h 12m
seated Sep 06, 00:39 UTC
Top score
0.7232
0 is baseline speed
Leader
Held
incumbent kept the lead
5
| Role | Miner | Patch | Status | Score | Duration | Open |
|---|---|---|---|---|---|---|
| baseline | — | — | scored | 0 score breakdown | — | |
| leader |
| 5b56ceb…33e0d |
| scored |
| 0.7174 score breakdown |
| — |
| challenger | ddeb883…95ff5 | scored | 0.7232 score breakdown | — |
| challenger | bd0299d…ebdb3 | scored | 0.7187 score breakdown | — |
| challenger | 6c23743…49348 | disqualifiedengine died before becoming healthy (last error: [Errno 111] Connection refused); container log tail: PIServer pid=1) uvloop.run(run server(args)) (APIServer pid=1) File "/usr/local/lib/python3.12/dist-packages/uvloop/ init .py", line 96, in run (APIServer pid=1) return asyncio.run( (APIServer pid=1) ^^^^^^^^^^^^^^ (APIServer pid=1) File "/usr/lib/python3.12/asyncio/runners.py", line 195, in run (APIServer pid=1) return runner.run(main) (APIServer pid=1) ^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run (APIServer pid=1) return self. loop.run until complete(task) (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run until complete (APIServer pid=1) File "/usr/local/lib/python3.12/dist-packages/uvloop/ init .py", line 48, in wrapper (APIServer pid=1) return await main (APIServer pid=1) ^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/entrypoints/openai/api server.py", line 663, in run server (APIServer pid=1) await run server worker(listen address, sock, args, **uvicorn kwargs) (APIServer pid=1) File "/src/vllm/entrypoints/openai/api server.py", line 677, in run server worker (APIServer pid=1) async with build async engine client( (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=1) return await anext(self.gen) (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/entrypoints/openai/api server.py", line 99, in build async engine client (APIServer pid=1) async with build async engine client from engine args( (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter (APIServer pid=1) return await anext(self.gen) (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/entrypoints/openai/api server.py", line 135, in build async engine client from engine args (APIServer pid=1) async llm = AsyncLLM.from vllm config( (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/v1/engine/async llm.py", line 217, in from vllm config (APIServer pid=1) return cls( (APIServer pid=1) ^^^^ (APIServer pid=1) File "/src/vllm/v1/engine/async llm.py", line 146, in init (APIServer pid=1) self.engine core = EngineCoreClient.make async mp client( (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/tracing/otel.py", line 178, in sync wrapper (APIServer pid=1) return func(*args, **kwargs) (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/v1/engine/core client.py", line 132, in make async mp client (APIServer pid=1) return AsyncMPClient(*client args) (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/tracing/otel.py", line 178, in sync wrapper (APIServer pid=1) return func(*args, **kwargs) (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/src/vllm/v1/engine/core client.py", line 963, in init (APIServer pid=1) super(). init ( (APIServer pid=1) File "/src/vllm/v1/engine/core client.py", line 573, in init (APIServer pid=1) with launch core engines( (APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^ (APIServer pid=1) File "/usr/lib/python3.12/contextlib.py", line 144, in exit (APIServer pid=1) next(self.gen) (APIServer pid=1) File "/src/vllm/v1/engine/utils.py", line 1213, in launch core engines (APIServer pid=1) wait for engine startup( (APIServer pid=1) File "/src/vllm/v1/engine/utils.py", line 1272, in wait for engine startup (APIServer pid=1) raise RuntimeError( (APIServer pid=1) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {} | — score breakdown | — |
19/19 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.
Incumbent
2/2Loading weights and waiting for the server to answer.
Candidate 1 of 3
2/2Loading weights and waiting for the server to answer.
Candidate 2 of 3
2/2Loading weights and waiting for the server to answer.
Candidate 3 of 3
2/2Loading weights and waiting for the server to answer.
Scorer
2/2Loading weights and waiting for the server to answer.
Drift baseline
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.
Full workload replay against the latency gates.
The pinned baseline image teacher-forces captured outputs against the campaign thresholds.
Full workload replay against the latency gates.