Merge origin/main: reconcile the frank-zealot reslice with the dedupe pass
main moved under this campaign — PR #25/#26 resliced the RTX 3090 endpoint. The frontmatter conflict is resolved in favour of the live shape, confirmed by re-probe the same day: `--ctx-size 602112 --parallel 3` (3 × 200,704), `--cache-type-k f16 --cache-type-v q8_0`, `--spec-type draft-mtp`, `--jinja --reasoning auto`, `--metrics`. The 262,144 figures that remain on the page are era rows and the checkpoint's trained window, not the live shape. log.md's 2026-10-19 fleet-state bullet now records both probes and the law this taught: a docs pass that reports live shapes must re-probe before writing the number, because main moving mid-campaign makes the first probe stale.
This commit is contained in:
Frank
@@ -4,15 +4,15 @@
|
||||
# qwen35 hybrid with 32 layers (8 full-attention + 24 Gated DeltaNet) and the
|
||||
# MTP draft head INSIDE the file — via the PrismML fork build of llama.cpp
|
||||
# (vendor build 10777), the ONLY loader that registers the payload's custom
|
||||
# tensor type 142 and honours its prism.hadamard.* metadata: TWO 262,144-token
|
||||
# conversations (--ctx-size 524288 --parallel 2) over an UNQUANTIZED f16 KV
|
||||
# cache. Exact KV bills 32,768 B/token here, so the pool is what pays for it —
|
||||
# the same dtype at the old 786,432 pool is 24,576 MiB against the 24,123 MiB
|
||||
# the driver leaves addressable, and the slot count is the term that moved. The
|
||||
# publisher's own Q8_0 vision projector rides along (the BF16 one can crash on
|
||||
# concurrent images), and MTP stays OFF: the head is present, but exact KV
|
||||
# leaves no room for a draft context that bills f16 KV over the whole pool. Log
|
||||
# verbosity 4 ships so the VRAM-fit forensics land in the journal.
|
||||
# tensor type 142 and honours its prism.hadamard.* metadata: THREE 200,704-token
|
||||
# conversations (--ctx-size 602112 --parallel 3) over an f16 K + q8_0 V cache —
|
||||
# 25,088 B/token, 14,406.00 MiB at this pool — with the MTP drafter ARMED
|
||||
# (--spec-type draft-mtp). The asymmetry IS the shape: exact V (32,768 B/token)
|
||||
# leaves nothing for a draft context that bills its own f16 KV over the WHOLE
|
||||
# pool (4,096 B/position, 2,352.00 MiB here), and the 786,432 pool this shape
|
||||
# replaced cannot carry a drafter at any dtype inside the 24,123 MiB the driver
|
||||
# leaves addressable. The publisher's own Q8_0 vision projector rides along (the
|
||||
# BF16 one can crash on concurrent images). Log
|
||||
# This seam runs the serve script against a stub engine and asserts on the
|
||||
# argv it actually execs, so what is pinned is the command the operator gets.
|
||||
|
||||
@@ -143,7 +143,7 @@ run_stage() {
|
||||
done
|
||||
}
|
||||
|
||||
@test "two conversations share the pool at a 262144 window each" {
|
||||
@test "three conversations share the pool at a 200704 window each" {
|
||||
serve_argv
|
||||
[ "$status" -eq 0 ]
|
||||
[ "$(argv_value --alias)" = "frank-zealot" ]
|
||||
@@ -152,30 +152,36 @@ run_stage() {
|
||||
[ "$(argv_value --model)" = "$MODEL_DIR/$MODEL_STUB" ]
|
||||
[ "$(argv_value --n-gpu-layers)" -gt 0 ]
|
||||
# llama.cpp divides --ctx-size across slots, so the observable contract is
|
||||
# the per-slot window. Exact KV costs the SLOT COUNT, not the window: every
|
||||
# conversation still gets the model's TRAINED 262,144, and the harness
|
||||
# contextWindow must quote that number — the pool and the slot count are
|
||||
# neither, and a longer prompt is a 400, never a truncation.
|
||||
[ "$(argv_value --parallel)" -eq 2 ]
|
||||
[ "$(argv_value --ctx-size)" -eq 524288 ]
|
||||
local pool slots
|
||||
# the per-slot window: harness contextWindow, Prometheus dashboards and every
|
||||
# consumer's compaction trigger read THAT number, and a longer prompt is a
|
||||
# 400, never a truncation. Two invariants the pool/slot split has to keep:
|
||||
# it divides evenly (llama.cpp floors it otherwise) and a slot never exceeds
|
||||
# the model's TRAINED window (there is no YaRN here, so the engine would be
|
||||
# quoting a window it cannot fill).
|
||||
[ "$(argv_value --parallel)" -eq 3 ]
|
||||
[ "$(argv_value --ctx-size)" -eq 602112 ]
|
||||
local pool slots window
|
||||
pool="$(argv_value --ctx-size)"; slots="$(argv_value --parallel)"
|
||||
[ $((pool % slots)) -eq 0 ]
|
||||
[ $((pool / slots)) -eq 262144 ]
|
||||
window=$((pool / slots))
|
||||
[ "$window" -eq 200704 ]
|
||||
[ "$window" -le 262144 ]
|
||||
}
|
||||
|
||||
@test "the KV dtype pair follows the env file and flash-attn stays pinned on" {
|
||||
# Asserted against the env rather than a literal so a retune moves one
|
||||
# file, not two. The shipped pair is f16/f16: exact attention state, and the
|
||||
# slot count is what makes it affordable — this payload bills 8,192 elements
|
||||
# per token per cache (8 full-attention layers × 4 KV heads × 256 dim), so
|
||||
# exact KV is 32,768 B/token = 16,384.00 MiB at the 524,288 pool, where the
|
||||
# q8_0 pair this file used to ship billed 17,408 B/token = 13,056.00 MiB at
|
||||
# the old 786,432 pool (ledger-exact both times). The 24 DeltaNet layers
|
||||
# file, not two. The shipped pair is ASYMMETRIC — f16 K (the engine's own
|
||||
# default) plus q8_0 V: this payload bills 8,192 elements per token per cache
|
||||
# (8 full-attention layers × 4 KV heads × 256 dim), so K costs 16,384 B/token
|
||||
# and V 8,704 (q8_0 is 1.0625 B/element; there is no true fp8 KV dtype in
|
||||
# this build) = 25,088 B/token = 14,406.00 MiB at the 602,112 pool. Exact V
|
||||
# would bill 32,768 B/token and the all-q8_0 pair this file used to ship
|
||||
# billed 17,408 — the halfway rung is what pays for the third slot AND the
|
||||
# armed drafter (the fit gate below prices both). The 24 DeltaNet layers
|
||||
# bill a fixed recurrent state per slot (~50.25 MiB a cell), which is why
|
||||
# pool arithmetic alone under-prices the shape. flash-attn is not
|
||||
# decoration: the quantized-V fallback is only legal with it, so it stays
|
||||
# explicit and a dtype retune cannot silently fall back.
|
||||
# decoration: quantized V is only legal with it, so it stays explicit and a
|
||||
# dtype retune cannot silently fall back.
|
||||
local env_k env_v
|
||||
env_k="$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")"
|
||||
env_v="$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")"
|
||||
@@ -192,30 +198,47 @@ run_stage() {
|
||||
# The fit is arithmetic off the payload geometry plus the non-KV terms
|
||||
# measured off the boot ledger (weights 2,036.71 + compute buffers 1,409.02
|
||||
# + projector 595 + 248.10 + CUDA context ≈ 460 = 4,749 MiB, dtype- and
|
||||
# slot-independent at this ubatch), plus one ~51 MiB recurrent-state cell
|
||||
# per slot. 24,123 MiB is what the driver leaves addressable (nvidia-smi
|
||||
# reports it as used + free; its total column reads 24,576).
|
||||
local env_k env_v pool slots rate_k rate_v kv total
|
||||
# slot-independent at ubatch 2048), plus one ~51 MiB recurrent-state cell per
|
||||
# slot. That constant is deliberately NOT credited with the ~1,306 MiB the
|
||||
# shipped ubatch 1024 hands back: the gate stays conservative.
|
||||
# An ARMED drafter is billed, because it is the term this shape pays
|
||||
# CACHE_TYPE_V=q8_0 to afford: the draft context is built against the
|
||||
# TARGET's whole pool at its own f16 rate (measured 4,096 B/position at
|
||||
# blk.32) plus buffers and its own recurrent cells — the measured spec-ON
|
||||
# against spec-OFF delta at the 786,432 / ubatch-1024 arm was 3,524 MiB
|
||||
# beside 3,072 MiB of draft KV, i.e. ~452 MiB, doubled here for the third
|
||||
# slot's extra cells. 24,123 MiB is what the driver leaves addressable
|
||||
# (nvidia-smi reports it as used + free; its total column reads 24,576).
|
||||
local env_k env_v pool slots rate_k rate_v kv total spec f16 exact_pool exact_v
|
||||
env_k="$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")"
|
||||
env_v="$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")"
|
||||
pool="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
slots="$(sed -nE 's/^PARALLEL=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
spec="$(sed -nE 's/^SPEC_TYPE=(.+)$/\1/p' "$ENV_FILE")"
|
||||
rate_k="$(kv_bytes_per_token "$env_k")"
|
||||
rate_v="$(kv_bytes_per_token "$env_v")"
|
||||
f16="$(kv_bytes_per_token f16)"
|
||||
kv="$(( pool * (rate_k + rate_v) / 1048576 ))"
|
||||
total="$(( kv + 4749 + 51 * slots ))"
|
||||
if [ "$spec" != "none" ]; then
|
||||
total="$(( total + pool * 4096 / 1048576 + 768 ))"
|
||||
fi
|
||||
# The shipped arm has to leave real room: the projector's worst case is
|
||||
# charged AFTER the engine's own fit check, so a projection that lands on
|
||||
# the ceiling is a crash waiting for the first image request.
|
||||
[ "$total" -le $(( 24123 - 1024 )) ]
|
||||
|
||||
# And the gate must be able to REFUSE: the same exact KV at the pool this
|
||||
# shape left behind is 24,576 MiB of cache alone — a boot that dies before
|
||||
# /health ever answers. Proving the gate bites is what makes passing one
|
||||
# meaningful.
|
||||
local over
|
||||
over="$(( 786432 * (rate_k + rate_v) / 1048576 + 4749 + 51 * 3 ))"
|
||||
[ "$over" -gt 24123 ]
|
||||
# And the gate must be able to REFUSE, or passing above means nothing. Two
|
||||
# boots this shape can walk straight into: the retired dtype pair at the
|
||||
# retired pool (exact f16 at 786,432 = 24,576 MiB of cache alone, which died
|
||||
# at cudaMalloc), and the shipped pool with V moved back to f16 while the
|
||||
# drafter stays armed — 18,816 MiB of cache plus the draft's 2,352. Both die
|
||||
# before /health ever answers, and no health gate can see either.
|
||||
exact_pool="$(( 786432 * (rate_k + f16) / 1048576 + 4749 + 51 * 3 ))"
|
||||
[ "$exact_pool" -gt 24123 ]
|
||||
exact_v="$(( pool * (rate_k + f16) / 1048576 + 4749 + 51 * slots
|
||||
+ pool * 4096 / 1048576 + 768 ))"
|
||||
[ "$exact_v" -gt 24123 ]
|
||||
}
|
||||
|
||||
@test "log verbosity follows the env file" {
|
||||
@@ -277,48 +300,54 @@ run_stage() {
|
||||
argv_value --ubatch-size | grep -qE '^[0-9]+$'
|
||||
}
|
||||
|
||||
@test "speculation is off: no drafter flag reaches the argv" {
|
||||
# Frank, 2026-10-18: this file DOES carry the MTP head (the boot arms prove
|
||||
# it loads and drafts, acceptance 0.798/0.617 per position, mean accepted
|
||||
# length 2.41) and it is still off, because the draft context bills its own
|
||||
# f16 KV over the WHOLE pool — 4,096 B/position × 524,288 = 2,048 MiB plus
|
||||
# buffers — on a trunk that already projects 21,234 MiB with exact KV. The
|
||||
# MTP arms in frank-zealot.env are all q8_0-era measurements; the doors back
|
||||
# to the drafter are one window per conversation, or KV back to q8_0 with
|
||||
# UBATCH_SIZE=1024 (213.5 t/s). The flags move as a set:
|
||||
# SPEC_TYPE=none strips --spec-type, --spec-draft-n-max AND
|
||||
# --spec-draft-model together, so a no-spec boot cannot carry half a spec
|
||||
# pair (the ROCmFPX-era baseline arm segfaulted at load doing that).
|
||||
@test "the armed drafter ships the whole MTP set and no second copy of the trunk" {
|
||||
# Frank, 2026-10-19: the drafter is ON. The head is IN this file
|
||||
# (qwen35.nextn_predict_layers = 1, blk.32.nextn.*) and it accepted well
|
||||
# when it was measured off (0.798/0.617 per position, mean accepted length
|
||||
# 2.41); what it now pays for is CACHE_TYPE_V=q8_0 plus UBATCH_SIZE=1024,
|
||||
# which is why the dtype pair and the batch pair are pinned next door.
|
||||
# The observable contract is the SET: --spec-type plus every --spec-draft-*
|
||||
# the env names, and NO --spec-draft-model — the MTP draft rides the MAIN
|
||||
# model's weights, so a draft file would load the trunk a second time.
|
||||
local n_max
|
||||
n_max="$(sed -nE 's/^SPEC_DRAFT_N_MAX=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
serve_argv
|
||||
[ "$status" -eq 0 ]
|
||||
[ "$(argv_value --spec-type)" = "draft-mtp" ]
|
||||
[ "$(argv_value --spec-draft-n-max)" = "$n_max" ]
|
||||
[ "$(argv_value --spec-draft-n-min)" = "0" ]
|
||||
[ "$(argv_value --spec-draft-p-min)" = "0" ]
|
||||
! grep -qxF -- '--spec-draft-model' <<<"$output"
|
||||
}
|
||||
|
||||
@test "the rollback knob strips the entire spec set" {
|
||||
# SPEC_TYPE=none is the documented retreat (and the shape this endpoint
|
||||
# shipped before 2026-10-19). The law it exists to obey: the flags move as a
|
||||
# SET — a no-spec boot that keeps --spec-draft-n-max, or a baseline arm that
|
||||
# hands over --model-draft with no --spec-type, has segfaulted at load with
|
||||
# no diagnostic. So the rollback is proven by ABSENCE of all of them.
|
||||
serve_argv
|
||||
sed -i 's/^SPEC_TYPE=.*/SPEC_TYPE=none/' "$STAGE/test.env"
|
||||
run_stage
|
||||
[ "$status" -eq 0 ]
|
||||
! grep -qxF -- '--spec-type' <<<"$output"
|
||||
! grep -qxF -- '--spec-draft-n-max' <<<"$output"
|
||||
! grep -qxF -- '--spec-draft-n-min' <<<"$output"
|
||||
! grep -qxF -- '--spec-draft-p-min' <<<"$output"
|
||||
! grep -qxF -- '--spec-draft-model' <<<"$output"
|
||||
grep -qE '^SPEC_TYPE=none$' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@test "naming a drafter ships the MTP set, with or without a separate draft file" {
|
||||
# The documented MTP arm (frank-zealot.env): SPEC_TYPE=draft-mtp ALONE is
|
||||
# legal here because the head is IN the checkpoint and the draft context
|
||||
# rides the main model's weights — so --spec-draft-model must NOT appear,
|
||||
# or the trunk would be loaded twice.
|
||||
@test "an external drafter still reaches the engine as a complete set" {
|
||||
# The other arm the ROCmFPX-era crash was about: a named draft FILE must
|
||||
# arrive alongside --spec-type and the depth recipe, never alone. This
|
||||
# endpoint does not use it (the head is in the trunk), so the knob ships
|
||||
# empty and only this test sets it.
|
||||
serve_argv
|
||||
{
|
||||
echo 'SPEC_TYPE=draft-mtp'
|
||||
echo 'SPEC_DRAFT_N_MAX=2'
|
||||
} >> "$STAGE/test.env"
|
||||
run_stage
|
||||
[ "$status" -eq 0 ]
|
||||
[ "$(argv_value --spec-type)" = "draft-mtp" ]
|
||||
[ "$(argv_value --spec-draft-n-max)" = "2" ]
|
||||
! grep -qxF -- '--spec-draft-model' <<<"$output"
|
||||
|
||||
# And an external drafter still reaches the engine as a complete set — the
|
||||
# pair the ROCmFPX-era crash was about.
|
||||
echo "SPEC_DRAFT_FILE=$MODEL_DIR/$DRAFT_STUB" >> "$STAGE/test.env"
|
||||
run_stage
|
||||
[ "$status" -eq 0 ]
|
||||
[ "$(argv_value --spec-draft-model)" = "$MODEL_DIR/$DRAFT_STUB" ]
|
||||
[ "$(argv_value --spec-type)" = "draft-mtp" ]
|
||||
}
|
||||
|
||||
@test "vision ships by default and MMPROJ_FILE empty opts out of the image path" {
|
||||
|
||||
Reference in New Issue
Block a user