serverAppConfigs/serverAppConfigs-docs/LLM/dankserver-qwen38-fp8-expert-offload-tuning.md

---

type: research title: Qwen3.8-Flash-Next FP8 on tcclaviger — expert-offload decode tuning description: VERIFIED 2026-09-29 by measurement. The flag-level decode-tuning campaign on the ad hoc qwen-fp8 container (orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8, tcclaviger RDNA4 vLLM fork, 2x R9700): the >35 tok/s target is MET at 37.4-40.6 tok/s by turning prefetch OFF — telemetry measured its precision at 36%, wasting ~half of all gather traffic — while the original 26.8 tok/s incumbent (prefetch on) survived every other challenger. Residual upside is the fork's gather read path (effective ~6.5-9.5 GB/s vs 22.7 GB/s the link delivers at the same slab size). tags:

• dankserver
• r9700
• gfx1201
• qwen3.8
• fp8
• expert-offload
• speculative-decoding
• tuning timestamp: 2026-09-29

---

Qwen3.8-Flash-Next FP8 — expert-offload decode tuning

Question this page answers. On the tcclaviger RDNA4 vLLM fork serving orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8 across both R9700s, what runtime flags actually move decode at a 32k working point?

Answer in one line. 37.44–40.57 tok/s — the >35 target is met — by deleting --expert-prefetch 1. Expert-cache telemetry measured the prefetcher at 36% precision (36,720 slabs prefetched, 13,369 served): ~half of all gather traffic was useless copies, and the copies it "saved" would have been installs anyway. The prefetch-on incumbent (26.8 tok/s) survived every other challenger measured: gather geometry, spec depth, TunableOp, scheduler batch knobs, concurrency, ngram-only drafting.

This is the ad hoc qwen-fp8 container on Dankserver (rootless podman, image docker.io/tcclaviger/vllm:latest, engine v0.29.0.dev0+g2bdbbc8080), NOT the frank-primary systemd service — the R9V production unit is untouched, so no stop-and-mask was required for any of this. All numbers are decode tok/s measured from the server's own usage.completion_tokens / (wall - ttft) — SSE chunk counting is invalid under speculative decoding because rejected drafts change the accounting.

Deployment shape (the tuned incumbent)

Serve script on the host (/home/dank/serve_qwen_fp8.sh), env hooks in CAPS. PREFETCH must be unset (omitting the flag; the fork's default is off):

MODEL=/home/dank/models/Qwen3.8-Flash-Next-Uncensored-FP8   (~172.8 GiB, 131 shards)
IMAGE=docker.io/tcclaviger/vllm@sha256:da4029666668b90a0386c1ed23ea370c79916ad4e1a6ad1dd9db098b9fa069ea
# image ID 3322dbbbc96d; local alias qwen-fp8-runtime:tuned-20260929;
# the floating :latest tag moved once already — always launch by digest.
# repo tag of this state: qwen-fp8-tuned-20260929
--tensor-parallel-size 2  --max-model-len 32768  --gpu-memory-utilization 0.98
--kv-cache-memory-bytes 2147483648  --max-num-seqs 4  --enable-prefix-caching
--speculative-config '{"method":"mtp","num_speculative_tokens":4}'
# NO --expert-prefetch: measured 36% precision, ~50% wasted gather traffic

Published to the host LAN via the serve script's PORTMAP hook (PORTMAP=7773:7770): health and completions answer on http://192.168.0.235:7773 (verified host-side 2026-09-29; 256k config, decode 36.49/34.55/35.98 through the published path). Host port 7773 was chosen over 7770 because frank-primary (7770) is stopped but ENABLED — any future start would collide with a published 7770.

Device notes carried from the bring-up: --device /dev/dri must be the WHOLE directory (individual renderD nodes enumerate but refuse contexts — "No CUDA GPUs are available" while device_count() reports 2); the image entrypoint execs vllm serve itself.

The memory plan this produces (from the engine's own expert_plan.py log):

region	size
expert cache space	15.05 GiB = 6,574 slots x 2.344 MiB
VRAM-only resident layers	3.52 GiB (layers 0-2, 1,536 experts)
swap region	11.53 GiB (5,038 slots, 111-112/layer)
host-backed experts	52.74 GiB per rank, 23,040 experts
KV reserve (one max-len request +8%)	0.36 GiB of the 2 GiB pool
CUDA graphs	1.93 GiB (21 graphs; 1.32 GiB at --max-num-seqs 2)
runtime overhead	7.6 GiB (non-torch + buffers + activation)

Measured arms (2026-09-29)

Decode tok/s at 166 / 1087 / 4064 prompt tokens, median of 3 runs after a 64-token warm pass, temperature 0, max_tokens 256:

Arm	166	1087	4064	Acceptance	Verdict
MTP4, stock 8x16, PREFETCH OFF	40.57	37.44	37.57	54.0%	NEW INCUMBENT — target met
MTP4, stock 8x16, prefetch ON	26.80	25.15	26.81	60.7%	old incumbent (+51%/+40% worse)
MTP4, prefetch ON (re-check)	25.80	24.38	26.63	47.9%	reproduces (noise band ±1)
MTP4, prefetch ON, gather 16x32	24.30	22.77	24.11	50.3%	−9% — ruled out
MTP4, prefetch ON, gather 32x64	26.58	24.94	26.34	49.6%	parity — ruled out
MTP3, prefetch ON	24.47	24.41	24.44	66.7%	−9%, flat in ctx — ruled out
MTP6, prefetch ON	19.07	17.81	13.54	17.4%	collapses; crosses UVA threshold — ruled out
MTP4, prefetch ON, MNBT 8192	29.32	24.12	23.65	—	neutral — ruled out
MTP4, prefetch ON, PREFETCH depth 2	25.83	25.06	25.87	56.0%	neutral — ruled out
MTP4, prefetch ON, TunableOp w/ offload	23.59	(79.82*)	(79.89*)	(96.5%*)	rejected — corrupts
2-way concurrency, prefetch ON (2 streams)	—	—	15.06 + 23.11 = 25.49 summed	—	no gain vs 26.8 single
ngram-only drafter	—	—	—	—	fork bug: PLE inputs unprepared
256k ctx (MAXLEN=262144, KV 4.5 / 4.03 GiB, prefetch off)	36.65 / 36.48	34.21 / 34.13	34.77 / 35.02	53.0 / 39.4%	boots and serves; band 34.1-36.5 straddles 35 within noise; arena identical (5,648) at both KV sizes

* The TunableOp numbers are invalid by construction: the tuned GEMMs changed generated behavior (repetition-loop, the server's "repetition detected" halt firing at ~140-146 tokens instead of the full 256, acceptance jumping 60.7% → 96.5%), the 79.8 tok/s figures were measured on those halted degenerate completions, and the text-only check on a fresh prompt came back 20.01 tok/s — below baseline. GEMM autotuning that changes output text is broken tuning.

The decode curve without spec decode is dead flat 12.11 tok/s from 304 to 16,095 tokens — decode is context-independent on this shape, bound per-step by the expert gather, not by KV depth.

Telemetry — the measurement that found the win

R4D_LRU_TELEMETRY=1 arms per-layer counters; a torch-profiler window (/start_profile → traffic → /stop_profile) makes the fork log and write expert_cache_rank<N>.json beside the traces. torch_profiler_with_stack=false is mandatory in the profiler config — the default (true) grew a 6.5-min window's trace buffer ~40 GB and the kernel OOM-killed the engine core (anon-rss 95.2 GB, oom-kill in journalctl -k). The short window at 166 ctx (~15 s of traffic) completed cleanly with with_stack=false.

The fork's own numbers (102 steps, both ranks identical):

hit rate 0.8245 (137,084/166,262)   host installs 15,814
read-through 13,364                 prefetched 36,720
served by prefetch (migrations) 13,369

• The LRU is good: 82.45% hit rate overall; layers 0-2 pinned at 100%; swap-region layers 78-81%. The "arena holds only 27% of experts → 73% miss" arithmetic was wrong — temporal reuse carries it.
• The prefetcher is the poison: 36,720 slabs moved to serve 13,369 (36% precision). The 23,351 unused copies are ~0.7 GB/step/rank of pure waste — roughly half of all gather traffic — and the 13,369 "savings" would have been installs anyway. Depth-1 prefetch also cannot cover the ~2,400-slab per-step working set with its 16 slots/layer (768 total).
• Per-layer-step at a swap layer: ~30.6 routed, 24.8 hits, 3.3 installs, 2.6 read-through, 8.0 prefetched of which 1.7-3.3 useful.

The wall, measured

• PCIe link (pcie-link-probe): GPUs 03:00.0/07:00.0 LnkCap/LnkSta 32GT/s x16; root ports 00:01.1/00:01.3 cap x8. Effective Gen5 x8 = 31.5 GB/s/direction. rocm-smi pcie_link_speed: 25 is the ASPM idle downshift, not the loaded rate.
• H2D (HIP probe, pinned): 2.345 MiB (the engine's exact expert slab) 22.74 GB/s; 16 MiB 28.19; 1 GiB 28.74 (91% of ceiling). Pinned ≈ pageable — staging is not the lever. Single-transfer latency at slab size 105.7 µs vs 78 µs ideal → ~21% per-transfer overhead.
• Engine's effective gather rate: ~6.5-9.5 GB/s = 30-42% of what the link delivers at the same size. The bottleneck is the fork's read path (chunk/lane geometry, per-transfer cost), not the wire.
• Duty cycle: peak GPU util 100%, smooth ~29% with prefetch on — each step is ~100 ms of compute then hundreds of ms waiting on expert streaming. rocm-smi reports utilization, which reads ~0 while weights load during an arm's reload; VRAM is the honest panel there.

What the remaining flags cannot do (all measured)

• Gather geometry — 16x32 and 32x64 measured no better despite the fork's "tuned at the Gen4 ceiling" comment; the constants are already at parity on Gen5 x8. The read-path gap is structural, not a tuning knob.
• Spec depth — 4 is the optimum both ways (with prefetch on). Depth 6 additionally proves the UVA read-through path (step tokens > R4D_LRU_UVA_TOKENS=5) is slower than copy-in.
• Prefetch anything — depth 2 neutral, depth 1 the new negative; the tier is 3x too small for the working set and the predictor is 36% precise. expert_prefetch_k/budget/slots exist (defaults 20/14/16) but the precision result makes tuning them pointless.
• Arena growth via shrink — UTIL=0.99 fails boot (Free memory on device cuda:1 (31.29/31.86)); --max-num-seqs 2 fails CUDA-graph capture (Constraints violated (L['query_start_loc'].size()[0])); and the MNBT 8192 arm already proved a ~1 GiB arena shift is decode-neutral in both directions.
• Concurrency — under TP=2 both streams' tokens are computed on both cards, so each rank gathers the union of both streams' misses; the links do not add capacity and the shared arena thrashes. Summed 2-way (25.49) measured below single-stream (26.8) with prefetch on.
• ngram-only drafting — fails at engine init: RuntimeError: PLE inputs were not prepared; the fork prepares this model's PLE inputs only on the MTP spec path. Needs a fork patch, not a config.
• V-only q8 KV — stock --kv-cache-dtype offers fp8 variants only (K+V together); a V-only q8 needs a fork patch.

Fork bugs / traps found (for the engine authors or a future patch)

1. CLAV_TUNABLEOP_SWEEP=1 is silently skipped whenever expert offload is active unless CLAV_TUNABLEOP_WITH_OFFLOAD=1 is also set (tunableop_warmup.py).
2. TunableOp-with-offload, once forced on: +6.7 min warmup, no persistent cache (container-local), and corrupt numerics (repetition loops, early-EOS halts, invalid measurements). Rejected outright.
3. The torch-profiler stop path hangs the workers on ROCm when torch_profiler_with_stack is true (default): >10 min hangs on two attempts while the AsyncLLM wrapper reports "stopped successfully" in 1 s; the default stack-tracing grew a 6.5-min window's buffer ~40 GB and OOM-killed the engine core. With with_stack=false the stop completes and the telemetry report runs. The telemetry counters remain reachable ONLY through that profiler stop — no direct RPC trigger exists (telemetry_report has exactly one caller, gpu_worker.py).
4. ngram spec method does not prepare PLE inputs (above).

Where the headroom lives now

The 35 tok/s target is met (37.4-40.6) with prefetch off. What is left:

1. Fork patch to the gather read path — the ~6.5-9.5 → 22.7 GB/s software gap at slab size. If the gather reached wire rate, decode lands in the 60+ tok/s band before acceptance effects. Code work in expert_lru.py's gather (R4D_LRU_GATHER_* is read at import; the copy-in path itself is compiled — see /app/r4dhip/r4d.so).
2. 256k ctx — measured, final: boots at MAXLEN=262144 with KV_BYTES=4831838208 or 4328521728 alike — a 262,144-token window needs 4.0 GiB KV (hybrid attention + mamba pages ≈ 16 KiB/token, not the 32k plan's 9,190 B/token; 3 GiB boot-refuses and the engine estimates max len 184,224 at that pool; the exact-4.0 override loses ~20 MB to accounting and boots as 3.98 < 4.0). Decode band 34.1-36.5 across both KV sizes — the arena is identical (5,648 slots) at 4.5 and 4.03 GiB (the planner buckets; the trim went to margin, not slots), so the window costs ~10% decode vs the 32k config and no KV trim recovers it. The alternative that keeps the full 37.4-40.6 band is MAXLEN=184224 at 3 GiB KV. Correction: the planner sizes the arena AFTER the KV override (the earlier "before" reading was wrong) — the arena is what remains.
3. 2+ slots at long ctx — the KV pool post-spec holds ~66k tokens at 2 GiB (~2x 32k streams); concurrency summed below parity at 4064 ctx, so slots are a capacity feature, not a throughput one. Two full 256k streams need ~8-10 GiB of KV — that fits the arithmetic only by cutting the arena below usefulness; slots-at-256k is a fork-patch or smaller-payload question.

Reproducing

Host-side scratch scripts (2026-09-29): /home/dank/serve_qwen_fp8.sh (the serve script with all hooks), /home/dank/mtp_measure.py (usage-counter decode measure, 3 depths), /home/dank/mtp_measure_short.py (single depth, for profile windows), /home/dank/bench2way.py (concurrency), plus the arm scripts arm_*.sh / sweep_*.sh and the detached runner /home/dank/job.sh (outputs under /home/dank/jobs/NAME.out|.rc|.done). The measure scripts are podman cp'd into the container after every recreate (the serve script re-copies them; a recreate wipes container-local files).

2026-10-01 — production cutovers (qwen FP8+MTP4, then bf16 no-spec)

Two same-day cutovers moved this page's findings into production:

1. Qwen FP8 + MTP4 replaced the failed GLM/DFlash2 experiment (the GLM window is documented in frank-primary-glm53-flash-w4a16; git tag frank-primary-fp8-mtp-20261001 is the last commit of that shape). The production trio took MAXLEN 200000 x 3, fp8 KV, MTP4, prefetch off — measured 37.4-40.6 tok/s at ~54% acceptance.
2. The overnight redo campaign re-measured EVERY lever at matched geometry (prefetch OFF everywhere, MAXLEN 200000/SEQS 3/fp8 baseline) and concluded the day: the incumbent cutover to bf16 KV, no speculative decode (Frank's call).

What the redo campaign measured (all at shallow depth, 166/1087/4064)

lever	verdict
prefetch (re-confirmed)	the whole night's +40-51% lives in deleting it; the old 12.11 "no-spec baseline" was itself prefetch-taxed
gather geometry	R4D_LRU_GATHER_CHUNKS=32 / LANES=64 = +18.7% (49.25 @4064), the win GROWS with depth (39.5@166 -> 54.1@1087); g8x16 mild, g64x128 past peak
KV dtype	bf16 (auto) +4% decode on fp8-era numbers but halves attention-KV capacity (measured 14,047 vs 7,926 B/token; mamba states unaffected)
spec family	no-spec fastest once the tax was gone (41.46/41.29/41.47); MTP4's drafter reserves ~2.6 GiB/rank beside the pool; untaxed MTP re-measures never completed
MNBT	512 doubles TTFT (2.46 s vs 1.36 s @4064); 1024-4096 interchangeable; 12288 -2.5% + arena; locked 1024
UVA	2048 POISON (-39%); 8192 ~parity
arena	flat ±1.4% from ~6,830 down to ~5,500 slots; knee below
six slots	every SEQS-6 KV sizing refused at engine init

Depth caveat: every number above is at a near-empty KV. Deep-context behavior (the gather win growing with depth, bf16's decode cost at depth) is only sampled at 3 depths; a 64k-192k-depth probe is the flagged gap.

The deployed shape (2026-10-01: 5 x 262144, fp8, no spec)

FRANK_PRIMARY_MAXLEN=262144    x SEQS 4 (1,048,576 tokens of contract)
FRANK_PRIMARY_KV_BYTES=8311013376   PER RANK (fp8, pool scales with windows)
FRANK_PRIMARY_KV_DTYPE=fp8    --kv-cache-dtype fp8 (K and V together)
FRANK_PRIMARY_MNBT=1024       --max-num-batched-tokens 1024
R4D_LRU_GATHER_CHUNKS=32 / R4D_LRU_GATHER_LANES=64  (container env)
NO --speculative-config, NO --expert-prefetch

Boot-probed 2026-10-01 (transient systemd units at the production uid + memlock, full-log capture; the rootless bench probe had masked the production memory environment). The night searched two concurrency contracts:

rung	result
3 × 262144, bf16, KV 11,047,010,304	OOM at graph capture — Tried to allocate 76.00 MiB ... 0 bytes free, 30.43 GiB of 31.86 GiB already allocated by PyTorch
3 × 245760, bf16	OOM identically
3 × 237568, bf16	PASS — KV 718,606 tokens
3 × 241664, bf16	PASS — KV 732,359 tokens, 3.03x (max possible at 3 contexts)
6 × 241664, fp8	OOM — tried 10.70 GiB against 9.18 GiB free: six full-length contexts do NOT fit
5 × 262144, fp8	PASS on the first rung — KV 1,350,182 tokens, 5.15x
4 × 262144, fp8	DEPLOYED. Five slots booted but left 0 bytes free at runtime: a real client request (995-token prompt, max_tokens=261149) killed the worker (Tried to allocate 50.00 MiB ... 0 bytes free). Dropping one slot returns ~1.93 GiB per rank for activations and graph capture

Boot is NOT proof of runtime survivability: the five-slot shape passed every boot gate and still died on the first long-generation request. After any knife-edge shape change, send a request with a large max_tokens before calling it done. The deployed shape is four contexts of the model's full native 262,144 window. fp8 KV is what buys the capacity — 7,926 B/token against bf16's ~13,900-14,047 — at the cost of bf16's ~4 % decode edge. Six full-length contexts cannot fit at any KV dtype: the 6-seq graph/activation footprint leaves only 9.18 GiB for the pool, and 6 × 262144 needs 12.47 GB even at fp8.

The old "KV_BYTES is PER RANK, 9/16 GiB OOM" law was the MTP4 WORKSPACE reservation, not a VRAM wall. Failures are clean and diagnostic: the engine reports torch.OutOfMemoryError: Tried to allocate X GiB. GPU N has ... of which Y GiB is free, and the fork's giant ERROR lines are split by journald — read them via journalctl -o json, not -o cat (and podman logs, which is only available while the container lives).

Rollback to the 2026-09-29 fp8+MTP4 shape: git tag frank-primary-fp8-mtp-20261001 (env trio + seam re-pinned there).

See Also

• dankserver-frontier-moe-feasibility — the sibling feasibility page (which frontier MoE fits this box; the same PCIe-expert-stream wall at V4.1 scale)
• frank-primary-r9v-radiance-qwen38-q8 — RETIRED 2026-09-30 (the R9V fork era; production has been the tcclaviger fork since)
• x4-pair-experiment — the same residency law measured on a narrower link: streaming over PCIe loses, computing in RAM does not care
• Dual-R9700-Cooperation — the board swap that made TP=2 legal here