Claude 071fa361a3 docs: CCCL → Triton methodology transfer — parameter search translation table ...

Maps CCCL %RANGE% benchmark format to EngineX Triton autotune configs:
- prefix_prefill: ipt→BLOCK_M, tpb→num_warps
- triton_flash_attention: 8 configs safety filter by SMEM
- fused_moe: BLOCK_SIZE_M/N/K grid search from CCCL transform/reduce
- Execution plan: hardware confirm → grid search → filter → deploy
- Competitive advantage: systematic search vs guessing

2026-08-03 04:37:23 +00:00

..

server_recon

docs: document Qwen3.6-35B-A3B bootstrap failure and architecture analysis

2026-08-01 13:16:01 +00:00

CCCL_TO_TRITON_METHODOLOGY.md

docs: CCCL → Triton methodology transfer — parameter search translation table

2026-08-03 04:37:23 +00:00

paged_attention_kernel_architecture.md

[ARCH] CCCL-derived paged attention kernel architecture + Triton rewrite

2026-07-31 04:13:07 +00:00

SPECIALIZATION_ANALYSIS.md

[muh] kernel_map: full vllm→CCCL mapping with SMEM overflow detection

2026-07-31 11:13:33 +00:00