From 60a6f2d296a6c863aa2d7d70f7a491e7ba62edf1 Mon Sep 17 00:00:00 2001 From: biondizzle Date: Tue, 26 May 2026 11:03:57 +0000 Subject: [PATCH] update README: D5b per-row LSE, D3/D4 DONE --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index cbbc8f78..d7f59524 100644 --- a/README.md +++ b/README.md @@ -149,7 +149,7 @@ Summary | D2 | 🟡 Per-head DONE | Multi-query grid. Per-head launch works (cos 0.999998, n_h=1-64 hd=64, n_h=2-8 hd=128, n_h=2 hd=256). Multi-CTA grid blocked: `flat_divide` + `epilogue_tma_store` layout mismatch. Requires full tma_partition refactor into kernel. | | D3 | ✅ DONE | SWA sequence length mask (in-kernel post-QK via tTMEM_LOADcS coordinates, swa_len Int32 scalar) | | D4 | ✅ DONE | Causal mask on SWA branch (k_coord > m_coord → -inf, combined with D3 via OR logic) | -| D5 | 🟢 D5a+D5b DONE | D5a: normalize flag + LSE output (err=0.0). D5b: Python SWA+sink merge (cos 0.961). D5c/D5d: fused kernel merge TODO. | +| D5 | 🟢 D5a+D5b DONE | D5a: normalize flag + LSE output. D5b: Per-row LSE + Python KV merge (cos 0.999994). D5c/D5d: fused kernel merge TODO. | | E1-E7 | TODO | Production extraction (class, custom op, cache, cleanup) | | NVFP4-3 | ✅ DONE | `use_2cta_instrs` conditional in gemm_runner.py. 1.7-1.9× throughput at prefill shapes. |