ViperEkura/AstrAI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
734 Commits 1 Branch 14 Tags
69f35c46e063702e6ba4b6c69dd86c08e4967f57
Commit Graph
4 Commits
Author SHA1 Message Date
ViperEkura 0e7fe57d96 fix: use max_context_len for stable num_splits in paged decode 
- PagedKV::host_kv_len now returns max_context_len instead of max_seq_len
- Eliminates grid-z instability for CUDA graph capture/replay
- Restore skip_no_kernel re-export accidentally removed by ruff --fix
 2026-08-07 14:42:53 +08:00
ViperEkura 55ee258e95 style: fix ruff lint warnings 
- Remove unused local variable b in attention_backend.py
- Remove unused variable rank0_sd in test_broadcast_state_dict.py
- Remove unused imports across test files
 2026-08-07 14:17:48 +08:00
ViperEkura 738cb8f128 fix: broadcast ref/old model state_dict for FSDP 
- Add broadcast_state_dict to sync state_dict from rank-0 to all ranks
- Fix create_ref_model returning None on non-rank-0 under FSDP
- Fix sync_old_model only updating old_model on rank-0 under FSDP
- Split skip_no_cuda/skip_no_kernel markers and hoist to top-level conftest
- Add distributed tests for broadcast_state_dict and create_ref_model
 2026-07-31 08:32:22 +08:00
ViperEkura 3067a8e1a6 feat: unify attention backend with multi-dim mask support 
- Add attention() functional entry delegating to active backend
- GQA/MLA forward calls attention() instead of inline cache/SDPA
- CUDA kernels support 2D/3D/4D mask via mask_h_stride field
- CudaBackend.fwd_decode builds 2D padding mask for mixed seq_lens
- KVCache.max_len precomputed in bind_tasks to avoid GPU sync
- batch==1 decode short-circuits mask=None
- Split tests into conftest, test_backend, test_backend_equivalence, test_kernel_mask
- 440 tests pass, L20 decode 1.44-1.60x speedup vs torch native
 2026-07-30 20:38:34 +08:00