a88626c0ca
bench: refmatrix suite — ref count (1-9) x ref resolution ladder
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 16:34:35 -04:00
a4bd386e52
BENCHMARKS.md: final cross-GPU tables, failure stats, multi-ref rescue status
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 15:23:36 -04:00
c0a875423e
start-comfyui: expandable_segments allocator config (fragmentation OOM hygiene)
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 15:11:18 -04:00
4c2635515b
bench: --ref-downscale option — pre-shrink refs before the node (24GB OOM mitigation)
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 14:44:54 -04:00
a293d0a2c4
reliability: failure-stats + output-validation tooling; persistent output dir
...
- bench/failures.py: per-GPU success rates and error-class breakdown by config
- bench/validate_outputs.py: ffprobe every recorded output via /view
- finding: 24GB cards fail on multi-ref (TE vision OOM), not duration/size;
100% of successful runs produce valid videos
- outputs now written to /workspace (survives pod resets)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 14:41:00 -04:00
fbc68bb749
concurrency experiment measured: co-scheduling 13% slower than sequential — one worker per GPU confirmed
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 14:27:32 -04:00
24134b9653
BENCHMARKS.md: B200-complete results — bf16 fastest family, ref scaling, cross-GPU interim
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 14:16:13 -04:00
e90f64b30e
bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL
...
The CSV header predated the ref_count column so later rows were misaligned;
JSONL rows were always complete.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 13:51:17 -04:00
53b4a133e2
bench: survive server loss during polling (mark run failed, keep suite alive)
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 03:48:37 -04:00
427f2878c4
start-comfyui: per-host logs (shared volumes!), COMFY_ARGS passthrough
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 03:31:45 -04:00
58b4755475
start-comfyui: wait out mid-shutdown process before already-running check
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 03:23:09 -04:00
64e488fa49
start-comfyui: nohup fallback when tmux unavailable; parameterize port-forward
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 03:04:28 -04:00
3082ee796f
installer: fetch real bench images during pod bootstrap
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 03:01:30 -04:00
1debde7673
bench: v2 reference set — JP stills, Ashitaka/Bebop, forests, volcanos (up to 23k px)
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:45:34 -04:00
94a94a268f
docs: concurrency & cost-per-video report across GPU tiers
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:28:24 -04:00
c3cda1fb30
WEIGHTS.md: all 9 files persistent on 1TB volume, tmpfs scheme retired
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:12:42 -04:00
cc111c0c33
bench: real reference images (anime/film/panorama) replace synthetic gradients
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:10:27 -04:00
4a802d8c3e
bench: key-config suite with N=3 repeats for statistical averages
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:07:28 -04:00
3eb04b254b
remove accidentally committed pycache; ignore *.pyc/*.pyo
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:03:20 -04:00
d9b1f568bb
store ComfyUI configs in repo for one-command pod rebuild
...
- comfyui/: extra_model_paths.yaml + the three MiniMax H3 workflow JSONs
- push-to-pod.sh stages everything onto the persistent volume
- install-minimax-h3.sh rebuilds a wiped container from that stage
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 02:01:32 -04:00
2d6dbf9f81
pod reset recovery: new SSH port, consolidated downloads to 1T volume, retire tmpfs overflow
...
The network volume was resized to 1TB (which reset the pod and wiped the
container disk). All weights now live persistently on /workspace; the
/dev/shm overflow scheme is no longer needed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 01:58:41 -04:00
548e4efcaf
benchmarking info
2026-08-06 01:49:26 -04:00
52f8a79f35
bench: multi-reference ref2v support (1-8 ref images, match/max sizing)
...
- refheavy suite: ref2v saturation with 1/4/8 refs, the priority modality
- family suite: reduced grid for int8/bf16 family comparisons
- 8 distinct 1344x768 reference scenes generated into /ComfyUI/input
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 00:45:49 -04:00
23a755e394
docs: pad markdown table columns for raw-text readability
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 00:38:51 -04:00
9682b0a084
WEIGHTS.md: final download status — all 9 files present, none in progress
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 00:37:44 -04:00
225aa97620
MiniMax H3 on RunPod: install/download scripts, ComfyUI wiring, benchmark harness, research docs
...
- scripts/pod: weight downloads (workspace + tmpfs overflow for volume quota),
extra_model_paths.yaml, headless ComfyUI launcher, test image generator,
one-shot pod installer
- scripts/local: auto-reconnecting port forward for the ComfyUI panel
- bench: API-based harness for t2v/i2v/ref2v across durations, resolutions,
and weight families; CSV/JSONL results
- docs: WEIGHTS.md (what's downloaded where), RESEARCH.md (ComfyUI guides,
no-Comfy options via SGLang/vLLM/diffusers, concurrency model, serverless)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-08-06 00:28:16 -04:00
50417b5530
gitignore
2026-08-05 23:57:58 -04:00
97c263b27b
init
2026-08-05 23:54:47 -04:00
Hanashi