fix(run-swift15-bf16): per-mode engine pins + explicit KV pools
kld stays on 1.0.13 (record on the scoring engine) with --vram-kv-mib 4608 + 16 slots: the ratio-derived pool came up SHORT by 217 MiB at 32x16k. calib moves to 1.2.0: the RADIANCE_CALIB_TOKENS tap is a 1.2.0 qwen4exp plugin feature (1.0.13 plugin has the DIR half only), and Grams are bf16 activations - engine-invariant. --vram-kv-mib 9984 covers 64x16k fp8 slots.
This commit is contained in:
@@ -21,7 +21,8 @@
|
|||||||
set -uo pipefail
|
set -uo pipefail
|
||||||
|
|
||||||
MODE="${1:?usage: run-swift15-bf16.sh kld|calib}"
|
MODE="${1:?usage: run-swift15-bf16.sh kld|calib}"
|
||||||
IMAGE="stilldeadcode/radiance@sha256:4c3f484564bb2872784e46b0a59cbd71becc9c1e746e301a3596ffae253c322e"
|
PIN_1013=sha256:4c3f484564bb2872784e46b0a59cbd71becc9c1e746e301a3596ffae253c322e
|
||||||
|
PIN_120=sha256:665775ed1d90de6dbb25558e07fc60d20328f1346f96f3c6e00845eb763f01fa
|
||||||
RAD=/home/dank/models/rad/qwen4exp-swift15-bf16.rad
|
RAD=/home/dank/models/rad/qwen4exp-swift15-bf16.rad
|
||||||
C=swift15ref
|
C=swift15ref
|
||||||
LOG=/home/dank/logs/swift15_bf16.log
|
LOG=/home/dank/logs/swift15_bf16.log
|
||||||
@@ -44,16 +45,28 @@ ARGS=(--model /models/rad/qwen4exp-swift15-bf16.rad
|
|||||||
|
|
||||||
case "$MODE" in
|
case "$MODE" in
|
||||||
kld)
|
kld)
|
||||||
|
# 1.0.13: the engine that will serve the candidate — the reference is
|
||||||
|
# recorded on the same engine that scores it. The ratio-derived KV pool
|
||||||
|
# (1.95 GiB) is SHORT by 217 MiB at 32x16k; the pair is explicit: 16 slots
|
||||||
|
# need 2.17 fixed + 1.87 GiB of fp8 KV, 4608 MiB carries the margin.
|
||||||
|
IMAGE="stilldeadcode/radiance@$PIN_1013"
|
||||||
mkdir -p "$KLD_REF_DIR"
|
mkdir -p "$KLD_REF_DIR"
|
||||||
ARGS+=(--kld-record /data/kld-ref --kld-corpus /data/kld.jsonl
|
ARGS+=(--kld-record /data/kld-ref --kld-corpus /data/kld.jsonl
|
||||||
--max-num-seqs 32 --max-num-batched-tokens 32768)
|
--vram-kv-mib 4608
|
||||||
|
--max-num-seqs 16 --max-num-batched-tokens 32768)
|
||||||
;;
|
;;
|
||||||
calib)
|
calib)
|
||||||
|
# 1.2.0: the calibration tap (RADIANCE_CALIB_DIR + RADIANCE_CALIB_TOKENS)
|
||||||
|
# lives in the 1.2.0 qwen4exp plugin; 1.0.13 has only the DIR half with an
|
||||||
|
# unparameterisable threshold. Grams are bf16 activations — engine-invariant.
|
||||||
|
IMAGE="stilldeadcode/radiance@$PIN_120"
|
||||||
mkdir -p "$CALIB_DIR"
|
mkdir -p "$CALIB_DIR"
|
||||||
ARGS+=(--port 7770 --max-num-seqs 64 --max-num-batched-tokens 65536
|
ARGS+=(--port 7770 --vram-kv-mib 9984
|
||||||
|
--max-num-seqs 64 --max-num-batched-tokens 65536
|
||||||
--prefix-cache-dir /data/calib-kvcache)
|
--prefix-cache-dir /data/calib-kvcache)
|
||||||
;;
|
;;
|
||||||
probe)
|
probe)
|
||||||
|
IMAGE="stilldeadcode/radiance@$PIN_1013"
|
||||||
ARGS+=(--port 7770 --max-num-seqs 8 --max-num-batched-tokens 4096)
|
ARGS+=(--port 7770 --max-num-seqs 8 --max-num-batched-tokens 4096)
|
||||||
;;
|
;;
|
||||||
*) echo "unknown mode: $MODE" >&2; exit 2 ;;
|
*) echo "unknown mode: $MODE" >&2; exit 2 ;;
|
||||||
|
|||||||
Reference in New Issue
Block a user