diff --git a/CHANGELOG.md b/CHANGELOG.md
index f1445d16f..e604a09f5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.7.1] — 2026-07-15
+
+Patch release closing the two follow-ups disclosed in the v0.7.0 tag notes: the
+SQ8 vector CPU error-storm and replica TTL determinism.
+
 ### Fixed
 - **Vector: SQ8/TQ code-size mis-dispatch CPU error-storm.** SQ8's `bits()` returns 8,
   which falls outside TurboQuant's supported `1..=4` range; the free
diff --git a/Cargo.lock b/Cargo.lock
index 09aa29928..cd4c6a4c9 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1820,7 +1820,7 @@ dependencies = [
 
 [[package]]
 name = "moon"
-version = "0.7.0"
+version = "0.7.1"
 dependencies = [
  "anyhow",
  "arc-swap",
diff --git a/Cargo.toml b/Cargo.toml
index 5ff4115d4..f6bb12fdf 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "moon"
-version = "0.7.0"
+version = "0.7.1"
 edition = "2024"
 rust-version = "1.94"
 description = "A high-performance Redis-compatible server written in Rust"
diff --git a/RELEASES.md b/RELEASES.md
index c283d328b..05912e5be 100644
--- a/RELEASES.md
+++ b/RELEASES.md
@@ -1,5 +1,10 @@
 # Releases
 
+## v0.7.1 — 2026-07-15
+milestones: none (patch release folding in the two v0.7.0-tag-disclosed follow-ups)
+waivers: none new — `XSHARD-READ-01` remains the open GA gap (ROADMAP R4), unchanged from v0.7.0.
+evidence: Two correctness fixes shipped under one patch. (1) **Vector SQ8/TQ CPU error-storm (task #73, #334):** SQ8's `bits()=8` fell outside TurboQuant's `1..=4` range, so `code_bytes_per_vector` hit its `_ =>` arm returning `0` while emitting a `tracing::error!` on **every** call on the hot memory-accounting path — a CPU-pegging storm plus wrong resident-byte accounting for SQ8 indexes; dispatch now computes the true SQ8 layout directly and the free-fn warns at most once via an `AtomicBool` latch. (2) **Deterministic replica TTL (task #71, #335):** relative-expiry commands (`EXPIRE`/`PEXPIRE`/`SETEX`/`PSETEX`/`SET … EX/PX`/`GETEX … EX/PX`) are rewritten to absolute deadlines (`PEXPIREAT`/`SET … PXAT`) on the master before entering the durable log and replication stream, computed from the per-tick cached clock the handler used — so replicas and AOF replay reproduce the master's expiry *instant* (#71a); and a replica no longer runs its own active-expiry sweep, converging on the master's authoritative removal instead of racing an independent TTL cycle (#71b). This closes the replica relative-TTL caveat disclosed in the v0.7.0 tag. Both PRs green on the self-hosted CI matrix (Lint + Check + MSRV + Memory gate) and admin-squash-merged to `main` (f5641707, 389acb61). New unit coverage: 16 `expire_rewrite` transform tests + 2 black-box two-node replication TTL integration tests (`tests/replication_ttl_semantics.rs`).
+
 ## v0.7.0 — 2026-07-15
 milestones: v0.7.0 "Replication GA for multi-shard masters" (soak-gated tag; v0.6.1 hardening folded in)
 waivers: none — the v0.6.0 `shardslice-migration` waiver (was: expires 2026-08-01) is **retired**; lock-free cross-shard read work is now tracked as an open GA gap (`XSHARD-READ-01`, ROADMAP R4), not a time-boxed waiver.
diff --git a/docs/PRODUCTION-CONTRACT.md b/docs/PRODUCTION-CONTRACT.md
index c86096d92..a0b543bf9 100644
--- a/docs/PRODUCTION-CONTRACT.md
+++ b/docs/PRODUCTION-CONTRACT.md
@@ -127,7 +127,7 @@ per the CI gate · Blocking `—` = tracked but never blocks a tag (see Out of S
 | ✅ | WAIT-01 | `WAIT` reflects real replica ACK state | R1 (task #19, PR #282): replica 1s `REPLCONF ACK` ticker on the split PSYNC socket; master `ack_read_loop` + `drain_ack_offsets` record into `ReplicaInfo.ack_offsets`; connection-layer `try_handle_wait` blocks until ACK ≥ target or timeout. `wait_returns_acked_replica_count` e2e; exact on multi-shard masters too (summed snapshot offset). | GA |
 | ✅ | REPL-PLANES-01 | Every write plane replicates, not just KV: eviction/expiry DELs, Lua effects, graph, vector/text index defs+contents, WS.*, MQ.*, TEMPORAL.* | Wave A (PR #285): eviction/expiry DELs + Lua effects to both planes (EVAL was previously durable in neither). Wave B (PR #294 + task #34): WS/MQ deterministic records + replica apply + PSYNC registry blob. Graph plane (task #25): live GRAPH.* streaming + snapshot backfill. Suites: `tests/replication_planes.rs`, `replication_graph.rs`, `replication_mq.rs`, `replication_readonly_ws_mq.rs`. Unified poison-record policy for replica apply (task #48). | GA |
 | ✅ | REPL-SOAK-01 | 24h replication soak: kill -9 either side under WAIT-confirmed load, zero acked-write loss | **PASSED 2026-07-15** — `SOAK-PASS duration=86400s cycles=114 acked=82044 inflight=7 master_kills=57 replica_kills=57`; 82,044 WAIT-acked writes preserved across 114 alternating kill-9 cycles, zero acked-loss. Run dir `moon-soak/runs/20260714-141946`, RC `e2d87893`. Gates the v0.7.0 tag (task #65). | GA |
-| ⬜ | KEYSPACE-NOTIF-01 | `notify-keyspace-events` keyspace notifications | No implementation found in `src/`. ROADMAP v0.7.0 workstream R5 — deferred to v0.7.1 (one-headline rule). | GA |
+| ⬜ | KEYSPACE-NOTIF-01 | `notify-keyspace-events` keyspace notifications | No implementation found in `src/`. ROADMAP v0.7.0 workstream R5 — deferred to a later release (v0.7.1 was a patch: SQ8 CPU-storm + replica TTL determinism). | GA |
 | ⬜ | MONITOR-01 | `MONITOR` command | No implementation found in `src/command/`. ROADMAP v0.7.0 workstream R5. | GA |
 | ⬜ | XSHARD-READ-01 | Lock-free cross-shard read path (retire the shardslice waiver) | Waiver **expires 2026-08-01** per `RELEASES.md` v0.6.0 entry and ROADMAP §5; L4 redesign (`tmp/MULTISHARD-REDESIGN.md`) unstarted. ROADMAP v0.7.0 workstream R4. | GA |
 
diff --git a/docs/guides/clustering.md b/docs/guides/clustering.md
index 21a6d3305..8718cf642 100644
--- a/docs/guides/clustering.md
+++ b/docs/guides/clustering.md
@@ -178,16 +178,19 @@ Moon does not implement the Redis Sentinel protocol.
 - **Lazy backlog** — allocated only when the first replica handshake begins (REPLCONF), saving ~12 MB baseline memory
 - **Validated** — 24 h continuous-load kill-9 soak (alternating master/replica restarts), zero loss of any WAIT-acknowledged write
 
-!!! warning "Replica TTL semantics (v0.7)"
-    Relative-expire commands (`EXPIRE`, `SETEX`, `PEXPIRE`, `GETEX` with a relative
-    TTL) replicate verbatim rather than being rewritten to absolute `PEXPIREAT`, and
-    replicas run their own active-expiry cycle. Because the replica's countdown starts
-    when it **applies** the command — not when the master ran it — replication/apply
-    delay shifts a relative-TTL key's expiry moment by that delay **even with perfectly
-    synchronized clocks** (the replica holds the key slightly longer). Master/replica
-    clock skew adds a further offset on top. For exact cross-node expiry parity, set
-    absolute deadlines with `PEXPIREAT`. Absolute-rewrite + role-gated expiry land in
-    v0.7.1.
+!!! note "Replica TTL semantics (deterministic since v0.7.1)"
+    Relative-expire commands (`EXPIRE`, `SETEX`, `PEXPIRE`, `SET … EX/PX`, `GETEX`
+    with a relative TTL) are rewritten to absolute deadlines on the master
+    (`PEXPIREAT`/`SET … PXAT`) **before** they enter the durable log and replication
+    stream, using the master's per-tick cached clock — the exact value its command
+    handler stored. The replica (and an AOF replay after a restart) therefore
+    reproduces the master's expiry **instant**, not a countdown restarted at apply
+    time, so apply delay no longer shifts a key's expiry moment. A replica also no
+    longer runs its own active-expiry deletion sweep: it holds a logically-expired
+    key resident (reads still see it as gone) until the master streams the
+    authoritative removal, so both nodes delete at the same point in the stream.
+    Master/replica clock skew is thus the only remaining source of divergence, and it
+    affects only the wall-clock instant of deletion, not which node deletes first.
 
 ## Cluster mode