Stage
Scored
12 of 12 stages
Settled in
7h 21m
committed Sep 11, 03:16 UTC
Round score
0.8381
0 is baseline speed
p99 latency
—
ceiling 2000 / 50 ms
Round 39: scored · 0.8381
12/12 stages
Intake & gates
6/6Patch hash recorded; awaiting fetch.
{
"hotkey": "5Ey8nTvvDJ9fmKsJGqYCG88jGWMckWXFZT4rjyzDwgaUkogy",
"payment_tx": 6,
"commit_block": 9041564,
"payment_block": 9041561,
"patch_fingerprint": "sha256:1698c5004e6738b092d08826aec34ffd3e92d1043bcf88b93a0c714761616a33",
"patch_reveal_delayed": true
}A worker claimed the submission and started the pipeline.
{
"job_id": 130
}Patch artifact retrieved from object storage.
{
"size": 147990,
"patch_hash": "sha256:b4a9ead0e1e9b4ad915fce43352839aa47fb3e3748f40ad0398a0b0215dd7e5e"
}Integrity and path constraints checked.
{
"identity": "ok",
"patch_hash": "sha256:b4a9ead0e1e9b4ad915fce43352839aa47fb3e3748f40ad0398a0b0215dd7e5e"
}Patch applied onto the baseline checkout.
{
"ok": true
}Public API / surface compatibility held.
{
"files": [
"vllm/config/cache.py",
"vllm/engine/arg_utils.py",
"vllm/entrypoints/openai/api_server.py",
"vllm/entrypoints/openai/completion/protocol.py",
"vllm/entrypoints/openai/completion/serving.py",
"vllm/entrypoints/openai/serving_warmup.py",
"vllm/model_executor/layers/attention/attention.py",
"vllm/model_executor/layers/fla/ops/chunk.py",
"vllm/model_executor/layers/fla/ops/fused_recurrent.py",
"vllm/model_executor/layers/fla/ops/fused_sigmoid_gating.py",
"vllm/model_executor/layers/mamba/gdn/qwen_gdn_linear_attn.py",
"vllm/model_executor/layers/mamba/ops/causal_conv1d.py",
"vllm/model_executor/layers/quantization/utils/configs/N=14336,K=5120,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",
"vllm/model_executor/layers/quantization/utils/configs/N=16384,K=5120,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",
"vllm/model_executor/layers/quantization/utils/configs/N=34816,K=5120,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",
"vllm/model_executor/layers/quantization/utils/configs/N=5120,K=17408,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",
"vllm/model_executor/layers/quantization/utils/configs/N=5120,K=6144,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",
"vllm/platforms/interface.py",
"vllm/v1/attention/backends/gdn_attn.py",
"vllm/v1/core/sched/scheduler.py",
"vllm/v1/spec_decode/llm_base_proposer.py",
"vllm/v1/spec_decode/utils.py",
"vllm/v1/worker/gpu/attn_utils.py",
"vllm/v1/worker/gpu_model_runner.py",
"vllm/v1/worker/mamba_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@sha256:7ee8d8368ebce2bce537155c36a1eb2fc6085b0b879be8ad2e0c35101a569a9a",
"image_digest": "sha256:7ee8d8368ebce2bce537155c36a1eb2fc6085b0b879be8ad2e0c35101a569a9a"
}Candidate engine image built and digest pinned.
{
"mock": false,
"build_log": "/var/log/pareton/builds/073fbf79-043c-48ca-bfb8-21b64ad7282f/build.log",
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:7ee8d8368ebce2bce537155c36a1eb2fc6085b0b879be8ad2e0c35101a569a9a",
"image_tag": "ghcr.io/pareton-ai/pareton-engine:b4a9ead0e1e9b4ad915fce43352839aa47fb3e3748f40ad0398a0b0215dd7e5e"
}Round
3/3Waiting to be seated in a round.
No structured detail recorded for this step.
Seated in a round; waiting to run or running.
{
"ordinal": 39,
"round_id": "869c159d-fc71-44ec-a453-b40633a384a8"
}The image ran and holds a round score.
{
"score": 0.8380842900320729,
"reason": null,
"ordinal": 39,
"round_id": "869c159d-fc71-44ec-a453-b40633a384a8"
}