Decoder layer full block
Complete LLaMA decoder layer block fusing: input RMSNorm, multi-head GQA attention with RoPE, attention residual, post-attention RMSNorm, SwiGLU MLP, and MLP residual. This represents the atomic computational unit repeated across all layers.
Reported evidence · last observed 2026-07-24. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 18 cases · mean latencyone = 1 · head_dim = 128 · hidden_size = 4096 · kv_head_dim = 1024 · qkv_head_dim = 4096 · intermediate_size = 14336 · num_attention_heads = 32 · num_key_value_heads = 8 · num_key_value_groups = 418 cases
Not measured on H100 for this workload. Challenges →
1840.7µs62% SOL1.00×Reported · license unknown · no source2026-07-24
Measured exactly what you asked. Reported by source; not independently reproduced.
2849.6µs63% SOL1.01×Reported · license unknown · no source2026-07-14
Measured exactly what you asked. Reported by source; not independently reproduced.
3990.2µs54% SOL1.18×Reported · license unknown · no source2026-07-16
Measured exactly what you asked. Reported by source; not independently reproduced.
41.13ms48% SOL1.35×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
51.16ms50% SOL1.38×Reported · license unknown · no source2026-08-22
Measured exactly what you asked. Reported by source; not independently reproduced.
61.16ms50% SOL1.38×Reported · license unknown · no source2026-08-20
Measured exactly what you asked. Reported by source; not independently reproduced.
71.17ms49% SOL1.39×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
81.17ms49% SOL1.39×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
91.19ms49% SOL1.41×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
101.19ms49% SOL1.42×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
111.21ms48% SOL1.44×Reported · license unknown · no source2026-08-22
Measured exactly what you asked. Reported by source; not independently reproduced.
121.21ms48% SOL1.44×Reported · license unknown · no source2026-08-19
Measured exactly what you asked. Reported by source; not independently reproduced.
131.21ms47% SOL1.44×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
141.22ms47% SOL1.45×Reported · license unknown · no source2026-08-16
Measured exactly what you asked. Reported by source; not independently reproduced.
151.22ms47% SOL1.45×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
161.22ms48% SOL1.45×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
171.23ms47% SOL1.46×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
181.23ms47% SOL1.47×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
191.23ms47% SOL1.47×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
201.24ms47% SOL1.47×Reported · license unknown · no source2026-08-23
Measured exactly what you asked. Reported by source; not independently reproduced.
211.24ms47% SOL1.48×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
221.26ms47% SOL1.49×Reported · license unknown · no source2026-08-23
Measured exactly what you asked. Reported by source; not independently reproduced.
231.26ms46% SOL1.50×Reported · license unknown · no source2026-08-20
Measured exactly what you asked. Reported by source; not independently reproduced.
241.28ms46% SOL1.52×Reported · license unknown · no source2026-08-22
Measured exactly what you asked. Reported by source; not independently reproduced.
251.33ms44% SOL1.58×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.
261.34ms44% SOL1.60×Reported · license unknown · no source2026-08-24
Measured exactly what you asked. Reported by source; not independently reproduced.
271.39ms44% SOL1.65×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
281.39ms43% SOL1.65×Reported · license unknown · no source2026-08-15
Measured exactly what you asked. Reported by source; not independently reproduced.
291.70ms33% SOL2.02×Reported · license unknown · no source2026-07-25
Measured exactly what you asked. Reported by source; not independently reproduced.
301.84ms32% SOL2.19×Reported · license unknown · no source2026-08-09
Measured exactly what you asked. Reported by source; not independently reproduced.
311.91ms30% SOL2.27×Reported · license unknown · no source2026-07-29
Measured exactly what you asked. Reported by source; not independently reproduced.
3221.0ms4% SOL25.00×Reported · license unknown · no source2026-07-26
Measured exactly what you asked. Reported by source; not independently reproduced.
3321.1ms4% SOL25.08×Reported · license unknown · no source2026-07-26
Measured exactly what you asked. Reported by source; not independently reproduced.