5 Commits

Author	SHA1	Message	Date
biondizzle	55f1ddd502	Update GETTING_CUDAGRAPH_READY.md and CUDA_GRAPH_SYNC_INVENTORY.md with full current status, multi-GPU stream fix, and next steps	2026-06-06 09:17:49 +00:00
biondizzle	ac213bdee8	Update docs: CUDA graph capture WORKING on all 8 GPUs, 0.28s/token (2x eager)	2026-06-06 08:29:40 +00:00
biondizzle	b4a59d0940	Update CUDA graph docs with current status, A/B split, buffer fixes, remaining blockers ... GETTING_CUDAGRAPH_READY.md: - Updated architecture section for A/B split (Graph A + eager attention + Graph B) - Updated Section D integration order with current progress - Added all recent violation fix commits CUDA_GRAPH_SYNC_INVENTORY.md: - Added Category 6 fixes: _l1_out_buf 2x fix, GEMM output pre-allocation, swizzle CUDA kernel, gsa scalar assignment, router BF16 fix - Added remaining blockers for next session - Updated CUDAGraphDecoder architecture description for A/B split - Added capture/replay flow description	2026-06-04 05:13:51 +00:00
biondizzle	5ea3aa3406	Update GETTING_CUDAGRAPH_READY.md and CUDA_GRAPH_SYNC_INVENTORY.md ... - L0 CUDA graph capture PASSES on B200 - All compute-forward sync violations fixed - 3/5 Section C hazards done, 2 deferred to Phase 2 - Full violation fix log with commits - Next steps: extend to all 61 layers + replay verification	2026-06-03 19:15:27 +00:00
biondizzle	ba68212fa7	Add CUDA graph readiness detector (Section A of GETTING_CUDAGRAPH_READY.md) ... - Grep for Section B sync patterns in hot path files - Method 1: run decode forward with torch.cuda.set_sync_debug_mode('error') - Method 2: attempt CUDA graph capture of L0 decode step - Full model load + prefill + warmup before detection - Results saved to /tmp/cuda_graph_readiness_results.json	2026-06-03 16:34:15 +00:00