nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
853 Commits 351 Branches 8 Tags
dc8a6616963f8231b6efba4832a03e596254c17b
Commit Graph
853 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
SolitaryThinker dc8a661696 [bugfix]: address verify-pass findings on the 1546 fix branch 
- recipe_fingerprint also excludes attention.resolved_backend (a silent
  runtime fallback must fail the gate in its cohort, not open a fresh
  ungated one); requested_backend stays in the hash; regression test
  extended to both runtime-resolved values.
- Legacy v1 configs no longer crash after the GPU measurement: identity
  fields are emitted only for config_schema_version=2 configs, and the
  comparator falls back to the legacy (model_id, gpu_type) cohort when a
  record carries no identity fields (partial identity still raises).
- 'recipe' removed from V2_OPTIONAL_METADATA_FIELDS: the generated recipe
  owns the key now; declaring it in a config fails validation loudly
  instead of being silently overwritten.
- Docs: stale 'until those land' paragraph reconciled with what this
  branch actually lands; baseline_status documented.
 2026-07-05 14:39:57 -07:00
SolitaryThinker e03864a852 [docs]: align example records with the merged identity taxonomy 2026-07-05 14:39:57 -07:00
SolitaryThinker 5902ab2669 [bugfix]: pin recipe_fingerprint to declared inputs and make cohort initialization loud 
Rebase of #1546 onto main resolved the identity taxonomy in favor of the
merged #1544 values (workload_id=wan-t2v-1.3b, variant_id=canonical,
benchmark_version=1, config_schema_version=2). On top:
- recipe_fingerprint() no longer hashes the runtime-resolved HF snapshot
  revision (kept in the recipe as audit metadata) — upstream repo commits
  with unchanged weights no longer churn the cohort and reset baselines.
- The no-baseline branch now emits a loud warning block and a
  machine-readable baseline_status=initialized_new_cohort field instead of
  an indistinguishable success, so cohort shifts never silently disable
  regression gating.
- Regression test: resolved revision must not change the fingerprint.
 2026-07-05 14:39:57 -07:00
Mac Lee 53ce043b32 [ci]: align remaining performance cohort consumers 2026-07-05 14:39:57 -07:00
Mac Lee 7b74b94ad4 [ci]: complete performance cohort identity 2026-07-05 14:39:57 -07:00
Mac Lee 752248e466 [ci]: tighten performance cohort identity 2026-07-05 14:39:57 -07:00
Mac Lee cc7848ab46 [ci]: add performance fingerprint cohorts 2026-07-05 14:39:57 -07:00
William Lin 76b0550c15 [ci]: run pre-commit on fork PRs without manual approval (#1555) 2026-07-05 14:18:16 -07:00
William Lin 384c1e9493 [misc]: update reseed-performance-baseline skill for the hf_store move (#1545 follow-up) (#1553) 2026-07-05 14:16:55 -07:00
William Lin b1dbcc93f6 [misc]: reformat fastvideo/performance to the repo yapf config (#1554) 2026-07-05 14:16:20 -07:00
William Lin b93833772e [ci]: guard against test directories no CI lane collects (#1552) 2026-07-05 14:07:38 -07:00
Mac Lee 30b523edd6 [ci] Normalize performance stage component metrics (#1475) (#1550) 2026-07-05 14:05:26 -07:00
Mac LeeandSolitaryThinker 6aab7f3832 [ci] cover Hunyuan 1.5 chat-list text preprocessing (#1518) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-07-05 12:05:25 -07:00
Mac Lee 9cd53fe5f8 [ci] Add metric-specific performance thresholds (#1545) 2026-07-05 12:04:33 -07:00
Mac Lee 6a32cf3a5e [ci]: expose LoRA extraction slash command (#1542) 2026-07-05 06:45:31 -07:00
William Lin 98be9b3da2 [bugfix]: address the three remaining #1447 review findings (#1549) 2026-07-05 06:43:27 -07:00
Mac Lee c53e85b767 [ci] Add v2 performance benchmark config identity fields (#1544) 2026-07-05 06:18:15 -07:00
William Lin 40a8bd2d3b [bugfix]: skip ThunderKittens kernels on aarch64 and document the kernel build matrix (#1548) 2026-07-05 06:13:11 -07:00
Mac LeeandSolitaryThinker 31aa115611 [bugfix]: preserve FSDP hooks for RMSNorm qk norms (#1513) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-07-05 04:15:49 +00:00
zainnhandSolitaryThinker 98ac10a528 [infra] Auto-rebuild CUDA images when docker/Dockerfile changes on main (#1526) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-07-04 16:25:46 -07:00
William Lin a5a6d171e5 [attn] Make FA4 explicit opt-in via FASTVIDEO_FA4 and delete the runtime fallback machinery (#1540) 2026-07-04 14:51:00 -07:00
William Lin 51ed1ea423 [build] Bump fastvideo-kernel pin to 0.3.2 (#1541) 2026-07-03 14:48:15 -07:00
Mac Lee 00ec3e7388 [bugfix]: compute VSA topk from padded blocks (#1517) 2026-07-03 14:16:51 -07:00
William Lin 0d626ef2d1 [kernel] Bump fastvideo-kernel pin to 0.3.1 and version the FA4 tile_mn port as 0.3.2 (#1539) 2026-07-03 14:11:08 -07:00
William Lin b36d0ef085 [infra] Add DGX Spark and multi-architecture CUDA support (#1447) 2026-07-03 13:41:43 -07:00
William Lin 10c8c5df4d [misc] reorg: relocate ui/ and performance_dashboard/ under apps/ (#1537) 2026-07-02 20:29:17 -07:00
William Lin 31e26abec4 [chore] release fastvideo-kernel 0.3.1 (#1520) 2026-06-30 12:25:27 -07:00
sumyyyyyandSolitaryThinker 9e83ba630c [kernel] Extract VSA utility functions into fastvideo_kernel (#1408) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-06-30 12:19:25 -07:00
William Lin fc02a9ce8e [ci] aarch64 kernel wheel: build for Blackwell (sm_100a/sm_120a), not Hopper (#1516) 2026-06-29 16:10:42 -07:00
William Lin 3d36160fc4 [bugfix] -fsigned-char so ThunderKittens compiles on aarch64 (Grace Hopper) (#1515) 2026-06-29 14:05:38 -07:00
William Lin a11ec43de2 [ci] build + publish aarch64 (Grace Hopper) kernel wheels alongside x86_64 (#1514) 2026-06-29 12:28:34 -07:00
William Lin 2656d6530c [bugfix] compile FP4 (attn_qat_infer) kernels for sm_120a only via per-arch split (#1508) 2026-06-29 11:07:27 -07:00
Kevin Lin e3f54e7169 [bugfix] Fix causal attention mask for Blackwell FP4 MMA column layout (#1506) 2026-06-28 20:36:40 -07:00
William Lin 4ba5681307 [bugfix] guard ThunderKittens Hopper kernels for non-sm_90a device passes (#1507) 2026-06-28 20:07:43 -07:00
alexzms 8c23c86994 [docs]: add raw-video preprocess script for the QAD MixKit recipe (#1487) 2026-06-28 18:01:13 -07:00
William Lin 78d606a3a7 [feat]: make VSA tile cache configurable for training (#1444) 2026-06-28 02:18:31 -07:00
William Lin c4e108de78 [docs]: modernize documentation build (#1503) 2026-06-28 02:02:09 -07:00
Kaiqin Kong 16bf2eaf77 [feat] Relativistic RoPE re-indexing for long causal rollouts (#1454) 2026-06-28 01:43:00 -07:00
William Lin 1d15d974fa [misc]: cleanup outdated or unneeded agent infrastructure (#1504) 2026-06-27 19:37:49 -07:00
alexzms 5e57868b76 [ci] train-framework model coverage: Cosmos/MatrixGame2 finetune grad-norm + Cosmos/LongCat/MatrixGame2 loading smokes (#1497) 2026-06-27 17:16:00 -07:00
William Lin 6be280c914 [bugfix]: fix docs build (#1502) 2026-06-27 13:00:09 -07:00
KyleNeverGivesUpandClaude Opus 4.8 3ccdec9798 [bugfix] Make enable_torch_compile_vae actually compile the Wan VAE (#1498) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-27 12:30:59 -07:00
Satyam Srivastava 8658f774f3 [docs] Restructure contributing CI/CD and testing docs (#1501) 2026-06-27 11:46:18 -07:00
Raghav K 4f3ad3f6df [perf] Default Wan VAE decode to bf16 (lossless, faster) (#1472) 2026-06-26 12:42:29 -07:00
William Lin b454aa56c3 [misc] fix pre-commit (#1500) 2026-06-26 12:39:28 -07:00
William Lin f9b8e30ff3 Update README.md 2026-06-26 09:23:30 -07:00
William Lin 0356205b84 [bugfix] revert fastvideo kernel version to 0.2.6 (#1495) 2026-06-25 03:52:43 -07:00
Kevin Lin 719a1879bd [bugfix] Remove incorrect V-row permutation in scaled_fp4_quant_trans_kernel (#1493) 2026-06-25 03:05:12 -07:00
Utkarsh RanjanandClaude Opus 4.8 b57180bf97 [bugfix] Warn when a requested attention backend is unsupported by a layer (#1254) (#1486) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-24 15:56:39 -07:00
William Lin 7cebf5f82c [ci] cap kernel wheel build parallelism to avoid runner OOM (#1483) 2026-06-23 14:17:56 -07:00