biondizzle/nvfp4-megamoe-kernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update STATUS.md: E1-E4 done

Browse Source
This commit is contained in:
biondizzle
2026-05-30 21:20:10 +00:00
parent c4b40dd06c
commit e162a2d112
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
STATUS.md
View File

@@ -23,10 +23,10 @@
## Stage E Checklist (from ROADMAP/NEXT_PRIORITIES_PART_2)
- [ ] **E1:** Wire `LayerCacheHandle` → `gather_compressed_kv`, `gather_all_compressed_kv`, `gather_swa_kv`, `num_query_heads`, `head_dim`
- [ ] **E2:** End-to-end smoke test through one full layer
- [ ] **E3:** Top-level `model/dsv4.py` (currently 2-line TODO)
- [ ] **E4:** Delete `torch.cuda.synchronize()` from fast path
- [x] **E1:** Wire `LayerCacheHandle` → `gather_compressed_kv`, `gather_all_compressed_kv`, `gather_swa_kv`, `num_query_heads`, `head_dim` ✅
- [x] **E2:** End-to-end smoke test through one full layer ✅ (SWA + CSA + HCA)
- [x] **E3:** Top-level `model/dsv4.py` ✅
- [x] **E4:** Delete `torch.cuda.synchronize()` from fast path ✅
- [ ] **E5:** Fold batch loop into kernel grid
- [ ] **E6:** FP4 output fusion for FMHA → wo_a
- [ ] **E7:** Lightning indexer FP4 tensor-core scoring