GEMM n128 k2048
General matrix multiply (GEMM) C = A @ B.T. Captured from Qwen 3 30B A3B moe.gate.
Reported evidence · last observed 2026-08-03. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 25 cases · mean latency50 cases
Not measured on H100 for this workload. Challenges →
15.03µs68% SOL1.00×Reported · license unknown · no source2026-08-03
Measured exactly what you asked. Reported by source; not independently reproduced.
25.27µs67% SOL1.05×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
35.30µs67% SOL1.05×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
45.32µs67% SOL1.06×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
55.41µs66% SOL1.08×Reported · license unknown · no source2026-08-23
Measured exactly what you asked. Reported by source; not independently reproduced.
65.43µs66% SOL1.08×Reported · license unknown · no source2026-08-20
Measured exactly what you asked. Reported by source; not independently reproduced.
75.43µs66% SOL1.08×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
85.43µs66% SOL1.08×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
8=5.43µs66% SOL1.08×Reported · license unknown · no source2026-07-23
Measured exactly what you asked; tied ranks share a number. Reported by source; not independently reproduced.
95.47µs66% SOL1.09×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
105.49µs66% SOL1.09×Reported · license unknown · no source2026-08-22
Measured exactly what you asked. Reported by source; not independently reproduced.
115.49µs66% SOL1.09×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
11=5.49µs66% SOL1.09×Reported · license unknown · no source2026-08-02
Measured exactly what you asked; tied ranks share a number. Reported by source; not independently reproduced.
125.51µs66% SOL1.10×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
135.52µs66% SOL1.10×Reported · license unknown · no source2026-08-23
Measured exactly what you asked. Reported by source; not independently reproduced.
145.63µs65% SOL1.12×Reported · license unknown · no source2026-08-01
Measured exactly what you asked. Reported by source; not independently reproduced.
155.64µs65% SOL1.12×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.
165.70µs65% SOL1.13×Reported · license unknown · no source2026-07-27
Measured exactly what you asked. Reported by source; not independently reproduced.
175.80µs65% SOL1.15×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
185.80µs65% SOL1.15×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
195.81µs65% SOL1.15×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.
205.82µs65% SOL1.16×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
215.83µs65% SOL1.16×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
225.84µs65% SOL1.16×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
235.84µs65% SOL1.16×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
245.86µs65% SOL1.16×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
255.88µs64% SOL1.17×Reported · license unknown · no source2026-08-01
Measured exactly what you asked. Reported by source; not independently reproduced.
265.91µs64% SOL1.17×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
275.92µs64% SOL1.18×Reported · license unknown · no source2026-07-27
Measured exactly what you asked. Reported by source; not independently reproduced.
285.92µs64% SOL1.18×Reported · license unknown · no source2026-07-29
Measured exactly what you asked. Reported by source; not independently reproduced.
296.00µs64% SOL1.19×Reported · license unknown · no source2026-07-24
Measured exactly what you asked. Reported by source; not independently reproduced.
306.33µs62% SOL1.26×Reported · license unknown · no source2026-07-18
Measured exactly what you asked. Reported by source; not independently reproduced.
316.36µs63% SOL1.26×Reported · license unknown · no source2026-08-22
Measured exactly what you asked. Reported by source; not independently reproduced.
326.41µs62% SOL1.27×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
336.46µs62% SOL1.28×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
346.49µs62% SOL1.29×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
356.51µs62% SOL1.29×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
366.71µs61% SOL1.33×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
376.79µs61% SOL1.35×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
386.98µs60% SOL1.39×Reported · license unknown · no source2026-08-22
Measured exactly what you asked. Reported by source; not independently reproduced.
397.00µs60% SOL1.39×Reported · license unknown · no source2026-07-25
Measured exactly what you asked. Reported by source; not independently reproduced.
407.19µs59% SOL1.43×Reported · license unknown · no source2026-07-19
Measured exactly what you asked. Reported by source; not independently reproduced.
417.45µs59% SOL1.48×Reported · license unknown · no source2026-07-19
Measured exactly what you asked. Reported by source; not independently reproduced.
428.08µs57% SOL1.61×Reported · license unknown · no source2026-07-13
Measured exactly what you asked. Reported by source; not independently reproduced.
438.26µs56% SOL1.64×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
448.45µs56% SOL1.68×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
459.98µs51% SOL1.98×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
4610.0µs51% SOL1.99×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
4710.4µs50% SOL2.06×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
4810.5µs50% SOL2.08×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
Implementations
Show all 74 implementations ›Showing all 74 implementations ⌄
Semantics
Also indexed as 004-gemm-n128-k2048 · reviewed as the same computation; every definition's cohorts are shown here, ranked separately.