Expand description
2026-09-29: The roofline estimate of one node’s time in one step, from its edge shapes and
formats: max(bytes / DRAM bandwidth, FLOPs / tensor peak). It ranks a Venn report’s rows
until measured profiles replace it.
Owner: metrale-circuit (venn). Invariants:
- Bytes are every edge the node reads or writes at
rowsrows, plus its weights, plus the state it reads and writes: the paged KV cache overcontext_tokensper sequence, the GatedDeltaNet and Mamba2 recurrent states (FP32, read and written once per sequence). - Routed experts read
E * (1 - (1 - k/E)^T)distinct experts’ weights forTtokens (uniform routing). - The peak is the MMA class of the node’s input activation: FP8 or NVFP4 activations run the FP8 / NVFP4 MMA; anything else (W4A16, W8A16, BF16) runs the BF16 MMA.
- Not counted: launch overhead, conv windows, KV writes beyond their input edges. A dim an op needs that the circuit lacks is an error, never a guess.
Structs§
- Cost
- 2026-09-29: One node’s estimate.
Enums§
- Cost
Error - 2026-09-29: Why a node could not be estimated.