frank-primary: prefix caching back ON — the OFF experiment did not fix the corruption
Frank: still corrupted at ~40k with --no-enable-prefix-caching deployed and mechanically verified (zero gdn_hip faults in the container serving that window, coherent 40,771-token boundary probe). The recurrence is FAULT-FREE, so the align-mode page re-seed is not the (only) mechanism and the mitigation bought whole-history re-prefill per turn for nothing. Revert: knob FRANK_PRIMARY_NO_PREFIX_CACHING commented out -> the serve branch renders --enable-prefix-caching (the shipped contract). The knob, the branch and the seam stay documented for a future fixed fork build. Open hypotheses recorded in the runbook: re-fed poisoned transcript (the same conversation cannot distinguish fixed from unfixed), or a second fault-free long-context path — fp8 KV at depth is the next suspect. Next diagnostic: fresh-conversation reproduction, then a KV-dtype A/B.
This commit is contained in:
Frank
@@ -175,7 +175,8 @@ FRANK_PRIMARY_KV_DTYPE=fp8
|
||||
FRANK_PRIMARY_MNBT=2048
|
||||
FRANK_PRIMARY_GATHER_CHUNKS=32
|
||||
FRANK_PRIMARY_GATHER_LANES=64
|
||||
# PREFIX CACHING IS OFF — THE FORK'S OWN NAMED MITIGATION (2026-10-05).
|
||||
# PREFIX CACHING: ON. An OFF experiment ran 2026-10-05 (below) and FAILED
|
||||
# to stop the corruption, so the historical flag is back.
|
||||
# MEASURED 2026-10-04, 18:46:07 PDT (5.6 h into the live boot, one running
|
||||
# request, prefix hit rate 48.1%): 48 gdn_hip state faults in one 0.6 s
|
||||
# burst, then the process-lifetime silence cap:
|
||||
@@ -212,10 +213,19 @@ FRANK_PRIMARY_GATHER_LANES=64
|
||||
# history instead of at most 3135 tail tokens (a full 40k context costs
|
||||
# tens of seconds of TTFT per turn at this shape's prefill rate). A silently
|
||||
# corrupted conversation is worse than a slower first token.
|
||||
# RE-ENABLE PATH: if the fork ships a fixed align path, set this to empty,
|
||||
# redeploy, and re-verify by taking one conversation past 40,768 tokens
|
||||
# (decode must stay coherent and podman logs must show zero gdn_hip lines).
|
||||
FRANK_PRIMARY_NO_PREFIX_CACHING=1
|
||||
# RESULT (2026-10-05, later that day): THE MITIGATION DID NOT WORK. With
|
||||
# --no-enable-prefix-caching deployed and mechanically verified (zero
|
||||
# gdn_hip faults, a 40,771-token single-request boundary probe coherent),
|
||||
# live long conversations STILL degraded at ~40k on the running endpoint
|
||||
# (Frank, direct). The container serving that window logged ZERO faults
|
||||
# while the corruption reproduced, so the align-mode page re-seed is not
|
||||
# the (only) mechanism — see the runbook's RESULT note for the open
|
||||
# hypotheses (re-fed poisoned transcript vs a fault-free long-context
|
||||
# path such as fp8 KV at depth). Cost bought nothing: caching is back ON.
|
||||
# The knob stays commented for a future fork build with a fixed GDN state
|
||||
# path: set 1, redeploy, re-verify past 40,768 tokens (one conversation
|
||||
# coherent AND zero gdn_hip lines).
|
||||
# FRANK_PRIMARY_NO_PREFIX_CACHING=1
|
||||
# UTIL is an ARENA lever: the fork plans `budget = device_total x util`, and at
|
||||
# 31.86 GiB/card every +0.01 is +0.32 GiB of expert cache (~+139 slots), and
|
||||
# 0.982 is Frank's standing law: NEVER 1.00. The 1.00 attempt (2026-10-03,
|
||||
|
||||
@@ -137,13 +137,14 @@ fi
|
||||
# available" while device_count() says 2). --ipc=host for the engine's shared
|
||||
# memory; memlock unbounded for the pinned host slabs.
|
||||
# The entrypoint already execs `vllm serve "$@"`, so no `serve` here.
|
||||
# Prefix caching: the fork's QFN mamba align path corrupts GDN SSM state
|
||||
# at ~40k tokens (2026-10-04, 48 gdn_hip state faults, one request — the
|
||||
# evidence block is in frank-primary.env). FRANK_PRIMARY_NO_PREFIX_CACHING
|
||||
# flips to the fork-named mitigation (--no-enable-prefix-caching); empty
|
||||
# keeps the historical flag. NO comment lines inside the backslash chain
|
||||
# below — a comment there terminates the continuation and the next line
|
||||
# runs as its own command (the 2026-10-05 exit-127 crash loop).
|
||||
# Prefix caching: ON — the shipped contract. FRANK_PRIMARY_NO_PREFIX_-
|
||||
# CACHING=1 flips to the fork-named mitigation (--no-enable-prefix-caching)
|
||||
# for the QFN align-mode GDN state fault; it was tried 2026-10-05 and
|
||||
# REVERTED the same day (live conversations still degraded at ~40k with
|
||||
# caching off and zero faults — see the evidence block in
|
||||
# frank-primary.env). NO comment lines inside the backslash chain below —
|
||||
# a comment there terminates the continuation and the next line runs as
|
||||
# its own command (the 2026-10-05 exit-127 crash loop).
|
||||
# The ${VAR:-word} / ${VAR:+word} double-expansion for the two directions is
|
||||
# AMBIGUOUS bash (${VAR:--flag} parses as a substring offset when set —
|
||||
# measured 2026-10-05: rendered "--no-enable-prefix-caching1"), so the flag
|
||||
|
||||
@@ -374,6 +374,25 @@ slower first token.
|
||||
192.168.0.112:8989 leg with FrankBook-Pro asleep (environmental,
|
||||
unrelated to this change; re-run `tests/e2e/run.sh` once the mini is up).
|
||||
|
||||
**RESULT — REVERTED THE SAME DAY.** With every mechanical check green
|
||||
(zero faults, coherent 40,771-token probe), live long conversations
|
||||
STILL degraded at ~40k on the running endpoint (Frank, direct
|
||||
observation). The container serving that window (`--no-enable-prefix-
|
||||
caching`, booted 2026-10-05 12:47 PDT) logged ZERO `gdn_hip` faults
|
||||
while the corruption reproduced — so this recurrence is **fault-free**:
|
||||
the NaN-state guard did not fire, which the re-seed theory requires.
|
||||
Open hypotheses, in order: (1) the poisoned transcript is being re-fed —
|
||||
corrupted assistant turns already in the history keep producing
|
||||
corrupted continuations even with perfect state, so the same
|
||||
conversation cannot distinguish fixed from unfixed; (2) a second
|
||||
long-context mechanism with no guard coverage — fp8 KV degradation at
|
||||
depth is the next suspect (a bf16-KV boot costs ~2× the pool per token
|
||||
and would settle it). Prefix caching is **back ON**
|
||||
(`FRANK_PRIMARY_NO_PREFIX_CACHING` commented out — the cost bought no
|
||||
fix). The knob and the serve branch stay for a future fork build with a
|
||||
fixed GDN path. Next diagnostic: reproduce on a FRESH conversation; if
|
||||
it still breaks at ~40k with zero faults, A/B the KV dtype.
|
||||
|
||||
### Shape F/G (2026-10-03): where the free VRAM actually is, and what forcing it cost
|
||||
|
||||
`rocm-smi` showed **3.57 GiB free per R9700** at the deployed shape E (28.28 GiB
|
||||
|
||||
@@ -142,16 +142,16 @@ DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
|
||||
grep -q '^FRANK_PRIMARY_CACHE_DIR=/home/dank/.cache/frank-primary$' "$ENV_FILE"
|
||||
grep -q '^FRANK_PRIMARY_GATHER_CHUNKS=32$' "$ENV_FILE"
|
||||
grep -q '^FRANK_PRIMARY_GATHER_LANES=64$' "$ENV_FILE"
|
||||
# Prefix caching is OFF (2026-10-05): with the flag on, the fork runs
|
||||
# QFN on mamba_cache_mode 'align', and its GDN state path went
|
||||
# non-finite mid-conversation (48 gdn_hip state faults, one request,
|
||||
# slot 42 heads 3/8, at the 13th 3136-token boundary = 40,768 — the
|
||||
# "~40k corruption" report). The fork's own guard names the mitigation:
|
||||
# --no-enable-prefix-caching. RAM was ruled out the same day (zero MCE,
|
||||
# in-band pattern stable, 4800 MT/s is the JEDEC floor). The evidence
|
||||
# block is FRANK_PRIMARY_NO_PREFIX_CACHING in the env file; re-enable
|
||||
# only with a fixed align path and a re-verification past 40,768 tokens.
|
||||
grep -q '^FRANK_PRIMARY_NO_PREFIX_CACHING=1$' "$ENV_FILE"
|
||||
# Prefix caching is ON (reverted 2026-10-05 the same day it was
|
||||
# disabled): the fork's QFN align-mode GDN state fault (48 gdn_hip
|
||||
# state faults, slot 42 heads 3/8, at the 13th 3136-token boundary =
|
||||
# 40,768 — the "~40k corruption" report) was mitigated with
|
||||
# --no-enable-prefix-caching, but live long conversations STILL
|
||||
# degraded at ~40k with caching off and zero faults logged — cost
|
||||
# with no fix, so the historical flag returned. The knob stays
|
||||
# commented in the env file for a future fixed fork build; flip it to
|
||||
# 1 only together with a re-verification past 40,768 tokens.
|
||||
grep -qE '^# FRANK_PRIMARY_NO_PREFIX_CACHING=1$' "$ENV_FILE"
|
||||
grep -q '^FRANK_PRIMARY_MODEL_SHARDS=131$' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@@ -175,9 +175,10 @@ DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
|
||||
# explicitly in the serve script (the ${VAR:--flag} double-expansion is
|
||||
# ambiguous bash — when set it parsed as a substring offset, measured
|
||||
# 2026-10-05): set -> --no-enable-prefix-caching (the fork-named
|
||||
# mitigation), unset -> the historical --enable-prefix-caching. Both
|
||||
# directions are spelled out so a fork default change cannot silently
|
||||
# flip the contract.
|
||||
# mitigation, tried and REVERTED the same day — live corruption
|
||||
# persisted at ~40k with zero faults), unset -> the shipped
|
||||
# --enable-prefix-caching. Both directions are spelled out so a fork
|
||||
# default change cannot silently flip the contract.
|
||||
grep -qF 'FRANK_PRIMARY_PREFIX_CACHE_FLAG=--no-enable-prefix-caching' "$SERVE"
|
||||
grep -qF 'FRANK_PRIMARY_PREFIX_CACHE_FLAG=--enable-prefix-caching' "$SERVE"
|
||||
grep -qF '"$FRANK_PRIMARY_PREFIX_CACHE_FLAG"' "$SERVE"
|
||||
@@ -192,7 +193,7 @@ DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
|
||||
FRANK_PRIMARY_PREFIX_CACHE_FLAG=--enable-prefix-caching
|
||||
fi
|
||||
printf %s "$FRANK_PRIMARY_PREFIX_CACHE_FLAG"' _ "$ENV_FILE"
|
||||
[ "$output" = "--no-enable-prefix-caching" ]
|
||||
[ "$output" = "--enable-prefix-caching" ]
|
||||
grep -q -- '--trust-remote-code' "$SERVE"
|
||||
# DCP is opt-in: the flag is passed only when FRANK_PRIMARY_DCP is set
|
||||
# (DCP reuses the TP ranks when PCP is off, so TP=2 + DCP=2 fits two GPUs).
|
||||
|
||||
Reference in New Issue
Block a user