docs: qwen38-fp8 expert-offload tuning — prefetch off hits 37.4-40.6 tok/s (target met)
Measured campaign on the ad hoc qwen-fp8 container (tcclaviger RDNA4 fork, 2x R9700, TP=2): telemetry (with_stack=false) measured the prefetcher at 36% precision — ~half of gather traffic wasted; deleting --expert-prefetch: 26.8 -> 40.57/37.44/37.57 tok/s. Prefetch-on shape survived every other challenger (gather geometry, spec depth, TunableOp [corrupts numerics], MNBT, concurrency, ngram [PLE fork bug]). 256k ctx boots at 4.5 GiB KV (36.65/34.21/34.77, arena -14%). New runbook + index links + log entry.
This commit is contained in:
Frank
@@ -0,0 +1,244 @@
|
||||
---
|
||||
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:latest
|
||||
--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
|
||||
```
|
||||
|
||||
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 GiB, prefetch off) | 36.65 | 34.21 | 34.77 | 53.0% | boots; arena 6574→5648 (−14%) costs ~10%; 2 of 3 depths just under 35 |
|
||||
|
||||
\* 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**: boots at `MAXLEN=262144 KV_BYTES=4831838208`
|
||||
(a 262,144-token window needs **4.0 GiB** KV — hybrid attention +
|
||||
mamba pages cost ~16 KiB/token, not the 32k plan's 9,190 B/token;
|
||||
at 3 GiB the engine estimates max len 184,224). Decode
|
||||
36.65/34.21/34.77 — the arena pays 6,574→5,648 slots (−14%) and ~10%
|
||||
decode; 2 of 3 depths sit just under 35. The KV-exact 4.0 GiB override
|
||||
(0.5 GiB back to the arena, ~+3.5% slots) is the remaining nudge;
|
||||
the alternative is `MAXLEN=184224` at 3 GiB KV, which keeps the full
|
||||
37.4-40.6 band. 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).
|
||||
|
||||
## 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]] — the ACTIVE frank-primary
|
||||
(production is the R9V fork; this page's container is the ad hoc detour)
|
||||
- [[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
|
||||
@@ -101,6 +101,16 @@ frank-small, port 7771]
|
||||
bound, ~23 tok/s ceiling at today's residency). Includes the Affinity
|
||||
V4-Flash-to-V4.1 port assessment — reusable expert tiering, four
|
||||
architecture gaps, one of them a silent-wrongness trap on the Engram key
|
||||
- [[dankserver-qwen38-fp8-expert-offload-tuning]] — VERIFIED 2026-09-29:
|
||||
the flag-level decode-tuning campaign on the ad hoc qwen-fp8 container
|
||||
(tcclaviger RDNA4 fork, orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8,
|
||||
TP=2 across both R9700s). **>35 tok/s MET: 37.44-40.57 tok/s with
|
||||
`--expert-prefetch` DELETED** — telemetry measured the prefetcher at
|
||||
36% precision, wasting ~half the gather traffic (the LRU itself runs at
|
||||
82.45% hit). Prefetch-on incumbent 26.8 survived every other challenger
|
||||
(geometry, spec depth, TunableOp-corrupts, batch knobs, concurrency,
|
||||
ngram-fork-bug); the residual gap to ~60 tok/s is the fork's gather
|
||||
read path (6.5-9.5 GB/s effective vs 22.7 at the same slab size)
|
||||
- [[frank-medium-radiance-mxfp4]] — RETIRED 2026-09-26 (replaced by
|
||||
[[frank-primary-lucebox-ds4]], then
|
||||
[[frank-primary-llamacpp-qwen38-flash-next-q8]]): vllm-radiance 0.9.3
|
||||
|
||||
Reference in New Issue
Block a user