Stage
Scored
12 of 12 stages
Settled in
51h 04m
committed Sep 24, 02:30 UTC
Round score
0.665
0 is baseline speed
p99 latency
—
ceiling 2000 / 50 ms
Round 14: scored · 0.665
12/12 stages
Intake & gates
6/6Patch hash recorded; awaiting fetch.
{
"hotkey": "5G4AVs54rV7unZdSsPGcnAeWUV9UcqjcSpLP9rxR2g4Dp5HF",
"payment_tx": 2,
"commit_block": 9134537,
"payment_block": 9134534,
"patch_fingerprint": "sha256:3f1ff8d00e20ed04f8ed371bac08b28ddf15131b18b58a1739ad755ea4e3ee31"
}A worker claimed the submission and started the pipeline.
{
"job_id": 194
}Patch artifact retrieved from object storage.
{
"size": 647461,
"patch_hash": "sha256:e9b82cc33fd53ed28edfcaef0e9508ca97012b7c7b675ef1c595b70f08f19e3a"
}Integrity and path constraints checked.
{
"identity": "ok",
"patch_hash": "sha256:e9b82cc33fd53ed28edfcaef0e9508ca97012b7c7b675ef1c595b70f08f19e3a"
}Patch applied onto the baseline checkout.
{
"ok": true
}Public API / surface compatibility held.
{
"files": [
"python/sglang/kernels/ops/attention/fla/fused_sigmoid_gating_recurrent.py",
"python/sglang/kernels/ops/attention/fla/gdn_replayssm_deferred_fold.py",
"python/sglang/kernels/ops/attention/fla/gdn_replayssm_spec_decode.py",
"python/sglang/kernels/ops/attention/fla/layernorm_gated.py",
"python/sglang/kernels/ops/attention/triton_gdn_fused_proj.py",
"python/sglang/kernels/ops/mamba/causal_conv1d_triton.py",
"python/sglang/kernels/ops/sampling/sharded_gumbel.py",
"python/sglang/kernels/ops/speculative/__init__.py",
"python/sglang/kernels/ops/speculative/sn10_scatter_spec_extras.py",
"python/sglang/kernels/ops/speculative/topk1.py",
"python/sglang/srt/arg_groups/attention_hook.py",
"python/sglang/srt/arg_groups/speculative_hook.py",
"python/sglang/srt/distributed/device_communicators/fp8_a2a_all_reduce.py",
"python/sglang/srt/distributed/device_communicators/host_shm_ag_gemm.py",
"python/sglang/srt/distributed/device_communicators/host_shm_all_reduce.py",
"python/sglang/srt/distributed/parallel_state.py",
"python/sglang/srt/distributed/sn10_collective_hook.py",
"python/sglang/srt/entrypoints/openai/serving_completions.py",
"python/sglang/srt/environ.py",
"python/sglang/srt/layers/attention/flashinfer_backend.py",
"python/sglang/srt/layers/attention/hybrid_linear_attn_backend.py",
"python/sglang/srt/layers/attention/linear/gdn_backend.py",
"python/sglang/srt/layers/attention/linear/kernels/gdn_triton.py",
"python/sglang/srt/layers/attention/linear/sn10_extend_graph.py",
"python/sglang/srt/layers/attention/linear/sn10_shadow_fold.py",
"python/sglang/srt/layers/attention/mamba/mamba2_metadata.py",
"python/sglang/srt/layers/attention/sn10_gpu_plan.py",
"python/sglang/srt/layers/attention/sn10_kv_indices.py",
"python/sglang/srt/layers/attention/sn10_kv_rider.py",
"python/sglang/srt/layers/communicator.py",
"python/sglang/srt/layers/layernorm.py",
"python/sglang/srt/layers/logits_processor.py",
"python/sglang/srt/layers/quantization/fp8_utils.py",
"python/sglang/srt/layers/quantization/modelopt_quant.py",
"python/sglang/srt/layers/sampler.py",
"python/sglang/srt/layers/sharded_greedy.py",
"python/sglang/srt/layers/sharded_sampling.py",
"python/sglang/srt/layers/sn10_fp8_splitk.py",
"python/sglang/srt/layers/sn10_norm_quant.py",
"python/sglang/srt/layers/sn10_oproj_allgather.py",
"python/sglang/srt/layers/sn10_rank_pick.py",
"python/sglang/srt/layers/sn10_silu_nvfp4.py",
"python/sglang/srt/managers/io_struct.py",
"python/sglang/srt/managers/overlap_utils.py",
"python/sglang/srt/managers/schedule_batch.py",
"python/sglang/srt/managers/scheduler.py",
"python/sglang/srt/managers/scheduler_components/request_receiver.py",
"python/sglang/srt/managers/tokenizer_manager.py",
"python/sglang/srt/mem_cache/kv_cache_configurator.py",
"python/sglang/srt/mem_cache/mamba_slot_fused.py",
"python/sglang/srt/mem_cache/memory_pool.py",
"python/sglang/srt/mem_cache/unified_memory_pool.py",
"python/sglang/srt/model_executor/cpu_graph_runner.py",
"python/sglang/srt/model_executor/forward_batch_info.py",
"python/sglang/srt/model_executor/model_runner.py",
"python/sglang/srt/model_executor/runner/decode_cuda_graph_runner.py",
"python/sglang/srt/model_executor/runner/prefill_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/sampling/sampling_batch_info.py",
"python/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py",
"python/sglang/srt/speculative/eagle_draft_extend_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/sn10_draft_extend_prune.py",
"python/sglang/srt/speculative/sn10_fp8_draft_head.py",
"python/sglang/srt/speculative/sn10_side_commit.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@sha256:537136c56cd1bb639701212213c9ba53ebc182439f631782b0e1900ef81edf8c",
"image_digest": "sha256:537136c56cd1bb639701212213c9ba53ebc182439f631782b0e1900ef81edf8c"
}Candidate engine image built and digest pinned.
{
"mock": false,
"build_log": "/var/log/pareton/builds/b888363f-68fe-4f37-a7fd-5d0f7f7e46b4/build.log",
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:537136c56cd1bb639701212213c9ba53ebc182439f631782b0e1900ef81edf8c",
"image_tag": "ghcr.io/pareton-ai/pareton-engine:e9b82cc33fd53ed28edfcaef0e9508ca97012b7c7b675ef1c595b70f08f19e3a"
}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": 11,
"round_id": "f0ab8e2d-4502-4fe6-8a8f-eba5ac2df373"
}The image ran and holds a round score.
{
"score": 0.6666527591106906,
"reason": null,
"ordinal": 11,
"round_id": "f0ab8e2d-4502-4fe6-8a8f-eba5ac2df373"
}