Repository navigation

perf(dpa4): batch the SO3/grid contractions over (D,F); keep use_amp through pt_expt assembly - #5960

Merged

wanghan-iapcm merged 19 commits into

deepmodeling:masterfrom

wanghan-iapcm:perf-dpa4-grid-contract

Aug 17, 2026

Merged

perf(dpa4): batch the SO3/grid contractions over (D,F); keep use_amp through pt_expt assembly#5960
wanghan-iapcm merged 19 commits into
deepmodeling:masterfrom
wanghan-iapcm:perf-dpa4-grid-contract

Commits on Aug 4, 2026
- perf(dpmodel): contract the DPA4 grid-branch router with matmul
  Han Wang
  committed
  7518a41
- Revert "perf(dpmodel): contract the DPA4 grid-branch router with matmul"
  Han Wang
  committed
  01c58e6
- perf(dpmodel): stop broadcasting DPA4 so3 linear weights across nodes
  Han Wang
  committed
  193b49e
Commits on Aug 5, 2026
- perf(dpmodel): remove the remaining DPA4 broadcast-weight contractions
  Han Wang
  committed
  7545961
- fix(dpa4): serialize use_amp so a configured false is not silently ignored
  Han Wang
  committed
  3c2b9bf
- feat(pt_expt): honor enable_tf32 / DP_TF32_INFER like the pt backend
  Han Wang
  committed
  99d33ea
- perf(dpmodel): stop spelling the DPA4 grid router as a degenerate GEMM
  Han Wang
  committed
  504bb24
Commits on Aug 6, 2026
- Merge upstream/master into perf-dpa4-grid-contract
  Han Wang
  committed
  1270762
- docs: shorten the comments added by this branch
  Han Wang
  committed
  ae72043
- revert(dpmodel): restore master's GridBranch router line
  Han Wang
  committed
  1574442
- Revert "feat(pt_expt): honor enable_tf32 / DP_TF32_INFER like the pt backend"
  Han Wang
  committed
  1e56cf6
Commits on Aug 14, 2026
- Merge branch 'master' of github.com:deepmodeling/deepmd-kit into perf-dpa4-grid-contract
  Han Wang
  committed
  c1792fa
- fix(dpmodel): preserve empty batches in the degree-batched contraction
  Han Wang
  committed
  63071be
- fix(pt_expt): keep use_amp out of serialization, fix the assembly boundary
  Han Wang
  committed
  fa46570
- fix: address review round 2 (D,F batching, lossless compositions, test placement)
  Han Wang
  committed
  8bce829
- [pre-commit.ci] auto fixes from pre-commit.com hooks
  pre-commit-ci[bot]
  committed
  e2f54c8
Commits on Aug 15, 2026
- test,docs: pin the SO3/LoRA contraction contract and dedup the assembly invariant
  Han Wang
  committed
  81e756d
- Merge upstream/master into perf-dpa4-grid-contract
  Han Wang
  committed
  c958cd7
Commits on Aug 16, 2026
- refactor: drop the unused inner_potential_model injection point
  Han Wang
  committed
  d5bf63d

Commits

Commits on Aug 4, 2026

Commits on Aug 5, 2026

Commits on Aug 6, 2026

Commits on Aug 14, 2026

Commits on Aug 15, 2026

Commits on Aug 16, 2026