Stage
Scored
12 of 12 stages
Settled in
44h 27m
committed Oct 10, 07:10 UTC
Round score
0.6343
0 is baseline speed
p99 latency
—
ceiling 2000 / 50 ms
Round 15: scored · 0.6343
12/12 stages
Intake & gates
6/6Patch hash recorded; awaiting fetch.
{
"hotkey": "5Dr4a5Lj8BgWJWyRwjXGvybCBq4XRvh5pNcBqXsy5pfQzWCy",
"payment_tx": 18,
"commit_block": 9251130,
"payment_block": 9251127,
"patch_fingerprint": "sha256:4328d67b8026f2f957765600d3a9003049b17203c9fa6c4a8e40649638815070"
}A worker claimed the submission and started the pipeline.
{
"job_id": 231
}Patch artifact retrieved from object storage.
{
"size": 402217,
"patch_hash": "sha256:262598cd0c13ca9ca01090b53d41de4e7a7d2acec32782a1220df2d359314196"
}Integrity and path constraints checked.
{
"identity": "ok",
"patch_hash": "sha256:262598cd0c13ca9ca01090b53d41de4e7a7d2acec32782a1220df2d359314196"
}Patch applied onto the baseline checkout.
{
"ok": true
}Public API / surface compatibility held.
{
"files": [
"python/sglang/kernels/jit/csrc/attention/verify_attn_sm120.cuh",
"python/sglang/kernels/jit/csrc/gemm/fp8_blockwise/fp8_blockwise_scaled_mm_entry.cuh",
"python/sglang/kernels/jit/csrc/gemm/fp8_blockwise/fp8_blockwise_scaled_mm_sm120.cuh",
"python/sglang/kernels/jit/csrc/gemm/marlin/gptq_marlin.cuh",
"python/sglang/kernels/jit/csrc/gemm/marlin/marlin_template.h",
"python/sglang/kernels/ops/activation/silu_mul_quant.py",
"python/sglang/kernels/ops/attention/fla/gdn_replayssm_fused_verify.py",
"python/sglang/kernels/ops/attention/fla/layernorm_gated.py",
"python/sglang/kernels/ops/attention/verify_attn_sm120.py",
"python/sglang/kernels/ops/gemm/fp8_blockwise_gemm.py",
"python/sglang/kernels/ops/kvcache/kv_indices.py",
"python/sglang/kernels/ops/kvcache/nvfp4_kv.py",
"python/sglang/kernels/ops/layernorm/fused_add_rmsnorm_quant.py",
"python/sglang/kernels/ops/mamba/causal_conv1d_triton.py",
"python/sglang/kernels/ops/quantization/gptq_marlin.py",
"python/sglang/kernels/ops/speculative/__init__.py",
"python/sglang/kernels/ops/speculative/cache_locs.py",
"python/sglang/kernels/ops/speculative/chain_verify_tensors.py",
"python/sglang/kernels/ops/speculative/commit_steps.py",
"python/sglang/kernels/ops/speculative/ngram_block.py",
"python/sglang/kernels/ops/speculative/reject_sampling.py",
"python/sglang/kernels/ops/speculative/softmax.py",
"python/sglang/srt/arg_groups/attention_hook.py",
"python/sglang/srt/arg_groups/fields/spec.py",
"python/sglang/srt/arg_groups/kv_cache_hook.py",
"python/sglang/srt/arg_groups/speculative_hook.py",
"python/sglang/srt/environ.py",
"python/sglang/srt/layers/attention/flashinfer_backend.py",
"python/sglang/srt/layers/attention/linear/gdn_backend.py",
"python/sglang/srt/layers/layernorm.py",
"python/sglang/srt/layers/linear.py",
"python/sglang/srt/layers/logits_processor.py",
"python/sglang/srt/layers/quantization/fp4_kv_cache_quant_method.py",
"python/sglang/srt/layers/quantization/fp8.py",
"python/sglang/srt/layers/quantization/fp8_utils.py",
"python/sglang/srt/layers/quantization/marlin_utils_fp4.py",
"python/sglang/srt/layers/quantization/sm120_nvfp4_decode.py",
"python/sglang/srt/managers/scheduler_components/batch_result_processor.py",
"python/sglang/srt/managers/utils.py",
"python/sglang/srt/mem_cache/memory_pool.py",
"python/sglang/srt/model_executor/forward_batch_info.py",
"python/sglang/srt/model_executor/runner/decode_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/adaptive_cost_policy.py",
"python/sglang/srt/speculative/adaptive_runtime_state.py",
"python/sglang/srt/speculative/adaptive_spec_params.py",
"python/sglang/srt/speculative/base_spec_worker.py",
"python/sglang/srt/speculative/eagle_draft_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/ngram_worker.py",
"python/sglang/srt/speculative/qwen38_draft_vocab.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:c09277c596c1a333f6425f2e6d64f2007e5fc92df0ad10d49384443ad4baf792",
"image_digest": "sha256:c09277c596c1a333f6425f2e6d64f2007e5fc92df0ad10d49384443ad4baf792"
}Candidate engine image built and digest pinned.
{
"mock": false,
"build_log": "/var/log/pareton/builds/7c945704-cf86-4ba0-8790-2112cf1a7bd6/build.log",
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:c09277c596c1a333f6425f2e6d64f2007e5fc92df0ad10d49384443ad4baf792",
"image_tag": "ghcr.io/pareton-ai/pareton-engine:262598cd0c13ca9ca01090b53d41de4e7a7d2acec32782a1220df2d359314196"
}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": 13,
"round_id": "20031d2a-be1a-49bf-8cee-c49a77aea21a"
}The image ran and holds a round score.
{
"score": 0.6526262353722825,
"reason": null,
"ordinal": 13,
"round_id": "20031d2a-be1a-49bf-8cee-c49a77aea21a"
}