mirror of
https://github.com/ruvnet/RuView
synced 2026-08-01 19:01:42 +00:00
ruv
4ea8457017
Closes the Dense placeholder from earlier commits. Now both backends implement forward(); only SparseGqa supports streaming step()/KvCache, which is the structural gap dense MHA can't bridge by design. Dense path: - src/dense.rs new — DenseHead wraps upstream dense_attention. Stores causal flag and (cloned) config. forward() is a one-line delegation; no GQA dispatch (dense_attention upstream requires q_heads == kv_heads). - AetherTemporalHead::Dense changed from a unit variant to Dense(DenseHead). Construction succeeds for any valid TemporalHeadConfig where backend is Dense. - AetherTemporalHead.step() returns BackendDoesNotSupportStreaming for Dense — there is no dense-MHA-with-KV-cache equivalent and offering one would silently swallow the ADR-096 §3.2 structural argument. - AetherTemporalHead.make_cache() likewise — there's no cache to size for a dense kernel. Errors: - New TemporalError::BackendDoesNotSupportStreaming variant covers the Dense-step / Dense-make_cache cases. Specific so callers can fall back to forward() instead of giving up entirely. - TemporalError::DenseBackendNotImplemented retained for v0.1 back-compat (no consumers depend on it post-this-commit, but removing a public variant is a hard break). Future work can deprecate it once downstream callers move off. Tests (19/19 passing): - dense_backend_returns_typed_error → renamed and rewritten as dense_backend_forward_runs_with_matching_shape: constructs a Dense head, runs forward over (32, 4, 4, 16) Q/K/V, asserts output shape. - New dense_backend_step_returns_streaming_error: constructs Dense, attempts make_cache, expects BackendDoesNotSupportStreaming. - All 8 weight blob, 2 blob e2e, 3 streaming, 5 other smoke tests unchanged and still passing. This commit completes the ADR-096 §5 A/B gate: callers can now run the same Q/K/V through both backends and compare outputs / latency. The §5 four-gate validation (contrastive loss within 1%, rank-1 within 1pp, Spearman ≥0.95, latency ≥5×) becomes a runnable proposition, not a future task — though the actual gate run requires trained AETHER weights, which is its own track. Co-Authored-By: claude-flow <ruv@ruv.net>
29 lines
1.0 KiB
Rust
29 lines
1.0 KiB
Rust
use thiserror::Error;
|
|
|
|
#[derive(Debug, Error)]
|
|
pub enum TemporalError {
|
|
#[error("temporal head config invalid: {0}")]
|
|
InvalidConfig(&'static str),
|
|
|
|
/// Retained for back-compat with v0.1 callers; superseded by the
|
|
/// per-operation errors below now that Dense is implemented.
|
|
#[error("dense MHA backend not implemented yet (ADR-096 §4.4 follow-up)")]
|
|
DenseBackendNotImplemented,
|
|
|
|
/// Dense MHA has no notion of an accumulated KV cache — every
|
|
/// new frame requires recomputing the full N² attention matrix
|
|
/// (the structural gap ADR-096 §3.2 flagged). Callers that want
|
|
/// streaming decode must use the SparseGqa backend.
|
|
#[error("dense backend does not support streaming step(); use SparseGqa for online decode")]
|
|
BackendDoesNotSupportStreaming,
|
|
|
|
#[error("sparse attention kernel error: {0}")]
|
|
Kernel(String),
|
|
}
|
|
|
|
impl From<ruvllm_sparse_attention::AttentionError> for TemporalError {
|
|
fn from(e: ruvllm_sparse_attention::AttentionError) -> Self {
|
|
TemporalError::Kernel(format!("{e}"))
|
|
}
|
|
}
|