Stage
Scored
12 of 12 stages
Settled in
22h 10m
committed Sep 23, 08:16 UTC
Round score
0.6509
0 is baseline speed
p99 latency
—
ceiling 2000 / 50 ms
Round 11: scored · 0.6509
12/12 stages
Intake & gates
6/6Patch hash recorded; awaiting fetch.
{
"hotkey": "5Gy2ymrSM2CLiZhtM4oyfca4CBrmwq8Brbez4oAo8fcvB5Vc",
"payment_tx": 14,
"commit_block": 9129075,
"payment_block": 9129072,
"patch_fingerprint": "sha256:c56e5ec3c1aa06faf3b025377f17254260aa7c43a43c6e178e3b2413202d9985",
"patch_reveal_delayed": true
}A worker claimed the submission and started the pipeline.
{
"job_id": 192
}Patch artifact retrieved from object storage.
{
"size": 553960,
"patch_hash": "sha256:3a9245b4d68fc75e3a5a1b7ae56c5c82949e96b00589f8332af708a0031709b1"
}Integrity and path constraints checked.
{
"identity": "ok",
"patch_hash": "sha256:3a9245b4d68fc75e3a5a1b7ae56c5c82949e96b00589f8332af708a0031709b1"
}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/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_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_silu_nvfp4.py",
"python/sglang/srt/managers/io_struct.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/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/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@sha256:4c0797c78df4b787626693d61ffc964eecc1e40f9679cc5bf55639d86ef27990",
"image_digest": "sha256:4c0797c78df4b787626693d61ffc964eecc1e40f9679cc5bf55639d86ef27990"
}Candidate engine image built and digest pinned.
{
"mock": false,
"build_log": "/var/log/pareton/builds/4ef472cf-2497-4c6e-8b1d-7f539f164f9a/build.log",
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:4c0797c78df4b787626693d61ffc964eecc1e40f9679cc5bf55639d86ef27990",
"image_tag": "ghcr.io/pareton-ai/pareton-engine:3a9245b4d68fc75e3a5a1b7ae56c5c82949e96b00589f8332af708a0031709b1"
}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": 10,
"round_id": "f07450c7-1f4b-4cc5-8d9b-a3036c461f39"
}The image ran and holds a round score.
{
"score": 0.6632046424513612,
"reason": null,
"ordinal": 10,
"round_id": "f07450c7-1f4b-4cc5-8d9b-a3036c461f39"
}