The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Job manager crashed while running this job (missing heartbeats).
Error code: JobManagerCrashedError
Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
session_id string | op string | impl string | desc string | signature string | gpu string | arch string | dtype string | shape unknown | objective string | baseline_ms float64 | best dict | attempts dict | num_steps int64 | elapsed_s int64 | elapsed_hms string | trace list | messages list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
cuda_swiglu_act-a10-M=256,N=5632-bf16-s14559839 | swiglu_act | cuda | fused SwiGLU on packed gate_up[M,2N]: y = silu(gate) * up | swiglu_act(gu[M,2N] fp16) -> y[M,N] fp16 | a10 | sm_86 | bf16 | {
"M": 256,
"N": 5632
} | minimize latency_ms | 0.069604 | {
"step": 20,
"time_ms": 0.020091,
"speedup": 3.464
} | {
"kept": 7,
"reverted": 71,
"errors": 1,
"rebench": 3
} | 79 | 6,989 | 1:56:29 | [{"step":0,"tag":"v0_scalar","kind":"baseline","params":{},"status":"ok","time_ms":0.069604,"kept":t(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
cuda_minp_sample-rtx_5090-B=128,V=50257-fp16-s1448045 | minp_sample | cuda | min-p sampling: threshold = p*pmax, filtered cdf | minp(logits[B,V] fp16, p[B]) -> tok[B] | rtx_5090 | sm_120 | fp16 | {
"B": 128,
"V": 50257
} | minimize latency_ms | 0.149129 | {
"step": 21,
"time_ms": 0.021544,
"speedup": 6.922
} | {
"kept": 10,
"reverted": 22,
"errors": 1,
"rebench": 2
} | 33 | 4,625 | 1:17:05 | [{"step":0,"tag":"v0_serial","kind":"baseline","params":{},"status":"ok","time_ms":0.149129,"kept":t(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
cuda_topk_sample-a10-B=1,V=128256-fp32-s1740829 | topk_sample | cuda | top-k sampling over logits[B,V] with per-row k | topk(logits[B,V] fp16, k[B]) -> tok[B] | a10 | sm_86 | fp32 | {
"B": 1,
"V": 128256
} | minimize latency_ms | 0.022085 | {
"step": 17,
"time_ms": 0.007021,
"speedup": 3.146
} | {
"kept": 8,
"reverted": 31,
"errors": 0,
"rebench": 2
} | 39 | 3,723 | 1:02:03 | [{"step":0,"tag":"v0_insertion","kind":"baseline","params":{},"status":"ok","time_ms":0.022085,"kept(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
triton_swa_decode-rtx_a6000-B=32,H=32,Hkv=8,D=128,L=4096,W=512,SNK=4-bf16-s8466411 | swa_decode | triton | sliding-window paged decode attention with sink tokens (Triton) | "swa_decode(q[B,H,D], kc[NP,Hkv,PB,D], vc[NP,Hkv,PB,D], bt[B,LP] int32, lens[B] int32, W, SNK) -> o[(...TRUNCATED) | rtx_a6000 | sm_86 | bf16 | {
"B": 32,
"H": 32,
"Hkv": 8,
"D": 128,
"L": 4096,
"W": 512,
"SNK": 4
} | minimize latency_ms | 2.806251 | {
"step": 17,
"time_ms": 0.102731,
"speedup": 27.316
} | {
"kept": 5,
"reverted": 126,
"errors": 69,
"rebench": 14
} | 200 | 13,542 | 3:45:42 | [{"step":0,"tag":"v0_maskall","kind":"baseline","params":{},"status":"ok","time_ms":2.806251,"kept":(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
cuda_nucleus_sample-h100-B=1,V=128256-fp32-s16996168 | nucleus_sample | cuda | top-p sampling over logits[B,V] | nucleus(logits[B,V] fp16, p[B]) -> tok[B] | h100 | sm_90a | fp32 | {
"B": 1,
"V": 128256
} | minimize latency_ms | 0.015444 | {
"step": 26,
"time_ms": 0.005351,
"speedup": 2.886
} | {
"kept": 6,
"reverted": 47,
"errors": 2,
"rebench": 3
} | 55 | 4,893 | 1:21:33 | [{"step":0,"tag":"v0_greedy_sort","kind":"baseline","params":{},"status":"ok","time_ms":0.015444,"ke(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
cuda_rmsnorm-rtx_a6000-M=1,N=4096-fp16-s13170310 | rmsnorm | cuda | RMSNorm rows for decode/prefill: y = x/rms(x) * w | rmsnorm(x[M,N] fp16, w[N] fp16, eps f32) -> y[M,N] fp16 | rtx_a6000 | sm_86 | fp16 | {
"M": 1,
"N": 4096
} | minimize latency_ms | 0.005243 | {
"step": 22,
"time_ms": 0.003389,
"speedup": 1.547
} | {
"kept": 5,
"reverted": 76,
"errors": 3,
"rebench": 10
} | 84 | 7,032 | 1:57:12 | [{"step":0,"tag":"v0_scalar","kind":"baseline","params":{},"status":"ok","time_ms":0.005243,"kept":t(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
triton_nucleus_sample-rtx_a6000-B=1,V=32000-fp32-s1268690 | nucleus_sample | triton | nucleus top-p sampling: histogram-refined mass threshold + draw | nucleus_sample(logits[B,V]:fp16, p, u[B]:f32, temp) -> tok[B]:int32 | rtx_a6000 | sm_86 | fp32 | {
"B": 1,
"V": 32000
} | minimize latency_ms | 0.065615 | {
"step": 142,
"time_ms": 0.006416,
"speedup": 10.227
} | {
"kept": 9,
"reverted": 169,
"errors": 22,
"rebench": 7
} | 200 | 16,750 | 4:39:10 | [{"step":0,"tag":"v0_bitonic","kind":"baseline","params":{},"status":"ok","time_ms":0.065615,"kept":(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
cuda_rmsnorm-rtx_5090-M=1,N=4096-fp16-s6664408 | rmsnorm | cuda | RMSNorm rows for decode/prefill: y = x/rms(x) * w | rmsnorm(x[M,N] fp16, w[N] fp16, eps f32) -> y[M,N] fp16 | rtx_5090 | sm_120 | fp16 | {
"M": 1,
"N": 4096
} | minimize latency_ms | 0.005168 | {
"step": 30,
"time_ms": 0.003321,
"speedup": 1.556
} | {
"kept": 10,
"reverted": 76,
"errors": 2,
"rebench": 6
} | 88 | 7,779 | 2:09:39 | [{"step":0,"tag":"v0_scalar","kind":"baseline","params":{},"status":"ok","time_ms":0.005168,"kept":t(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
triton_gemm_fp16-rtx_a6000-M=1024,N=32000,K=4096-fp16-s6987342 | gemm_fp16 | triton | fp16 GEMM for prefill: C = A @ B with tl.dot tiles (Triton) | gemm(a[M,K] fp16, b[K,N] fp16) -> c[M,N] fp16 | rtx_a6000 | sm_86 | fp16 | {
"M": 1024,
"N": 32000,
"K": 4096
} | minimize latency_ms | 11.38006 | {
"step": 23,
"time_ms": 2.109104,
"speedup": 5.396
} | {
"kept": 7,
"reverted": 126,
"errors": 67,
"rebench": 13
} | 200 | 13,877 | 3:51:17 | [{"step":0,"tag":"v0_naive","kind":"baseline","params":{},"status":"ok","time_ms":11.38006,"kept":tr(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
cuda_embedding_gather-h200-T=512,D=8192,V=256000-bf16-s10973639 | embedding_gather | cuda | token embedding gather emb[idx[t]] -> y[t,:] | emb_gather(emb[V,D] fp16, idx[T] int32) -> y[T,D] fp16 | h200 | sm_90a | bf16 | {
"T": 512,
"D": 8192,
"V": 256000
} | minimize latency_ms | 0.018761 | {
"step": 11,
"time_ms": 0.007302,
"speedup": 2.569
} | {
"kept": 7,
"reverted": 32,
"errors": 1,
"rebench": 3
} | 40 | 3,731 | 1:02:11 | [{"step":0,"tag":"v0_scalar","kind":"baseline","params":{},"status":"ok","time_ms":0.018761,"kept":t(...TRUNCATED) | [{"role":"system","content":"You are a kernel optimization agent. Given an optimization task and the(...TRUNCATED) |
End of preview.