project6-dev
5efb0fcc35
feat(EX): corex_fa2.py — third dlopen module from comp 168 AST chain
Log analysis from dockerrizhi.txt (07-23 Sub168 run) reveals THREE
corex modules, not two:
1. corex_gdn.py — GatedDeltaNet fused kernel (already implemented)
2. corex_moe.py — MoE routing + expert GEMM (already implemented)
3. corex_fa2.py — FlashAttention2 dispatch (NEW)
corex_fa2.py handles 32/36 attention layers with three modes:
:333 → FA2 packed prefill (B=2 Hq=4 Hkv=1 D=256 max_q=2048)
:507 → FA2 paged chunked prefill (B=1 max_q=17 cache_blocks=2)
:225 → FA2 paged decode (B=1 max_k=45455 partition=256)
Wraps ixformer.contrib.vllm_flash_attn + ixf_F.vllm_single_query_cached_kv_attention.
These .so files EXIST in the base image (libixattn.so).
Also: wired corex_fa2 import into qwen3_5.py + deploy script.
2026-08-10 04:01:21 +00:00
..
2026-08-10 02:25:23 +00:00
2026-08-10 04:01:21 +00:00
2026-08-10 03:37:15 +00:00
2026-08-10 03:37:15 +00:00
2026-08-10 02:31:55 +00:00
2026-08-10 03:38:46 +00:00
2026-08-10 03:10:58 +00:00
2026-08-10 02:55:58 +00:00