-
Notifications
You must be signed in to change notification settings - Fork 0
Performance
Alex He edited this page Sep 1, 2026
·
10 revisions
Headline numbers for v0.10.0. Two HIP ISAs share one tree; build with an explicit HIP_ARCH (Getting started). Wall time moves with page-cache state; treat E2E as a band. Denoise GPU (HIP events) is the stable GPU figure.
In-tree copy: docs/PERFORMANCE.md.
| Preset | gfx1151 | gfx90a |
|---|---|---|
| fox-s2 E2E | 83–87 s | ~10.5 s |
| fox-fast E2E | ~95 s | ~18 s |
| 15 s cinematic E2E | 45.0 min | 12 min 33 s |
gfx1151 fox-s2 md5 is unchanged from v0.9.0: 1731f95c4aa582597cf83d57f46b8f9e.
# fox-s2 — HIP A/B smoke (gfx1151 md5 gate)
./h3 --profile -d /path/to/MiniMax-H3 \
-p "A red fox walks through fresh snow." \
--width 512 --height 512 --frames 22 --steps 2 --layers 35 --reuse 1 \
-o outputs/fox-s2.mp4
# fox-fast — upstream tutorial “first fast video”, without --show
./h3 --profile -d /path/to/MiniMax-H3 \
-p "A red fox walks through fresh snow in a pine forest. Medium tracking shot, natural winter light, realistic fur, soft footsteps and wind." \
--width 512 --height 512 --frames 22 --steps 20 --layers 45 --reuse 2 \
-o outputs/fox-fast.mp4--reuse 2 on 20 steps yields 11 DiT evaluations. Showcase fox uses --layers 50 --reuse 1 and is not the fox-fast scoreboard.
Long T2VA: Long video. gfx90a DiT is BF16 by default (H3_INT8_MLP=1 restores INT8).
| When | fox-s2 E2E | fox-fast E2E | What landed |
|---|---|---|---|
| 2026-08-18 | ~257 s | — | First HIP profile |
| 2026-08-19 | ~117 s | — | INT8 DiT, faster load I/O |
| 2026-08-22 | — | ~213 s | First fox-fast measure |
| v0.9.0 | 83–87 s | 95 s | WMMA kernels; weights in VRAM carveout |
| v0.10.0 | same on gfx1151 | ~18 s on gfx90a | Dual ISA; MI210 MFMA flash |