project6 e969aa0e1f revert(corex_gdn+qwen3_5): restore to ff3562b9 — no rewriting existing modules ...

Reverted the NO-FALLBACK rewrite of corex_gdn.py and qwen3_5.py.

Policy: do NOT rewrite modules that already exist in base image or
upstream_ref. If an interface doesn't match, fix the interface call
site — don't rewrite the entire module in pure PyTorch.

Base image has corex_gdn.py, corex_moe.py, corex_fa2.py with C++
backends. The right approach is to match their __init__ signatures,
not replace them with slower Python reimplementations.

2026-08-10 09:32:24 +00:00

..

__init__.py

feat(EX): Algorithm Factor Replacement Engine — dlopen-based CUDA kernel dispatch

2026-08-10 02:25:23 +00:00

corex_fa2.py

refactor(corex): rewrite 3 dlopen modules to use real ixformer::infer dispatch chain

2026-08-10 06:16:39 +00:00

corex_gdn.py

revert(corex_gdn+qwen3_5): restore to ff3562b9 — no rewriting existing modules

2026-08-10 09:32:24 +00:00

corex_moe.py

feat(moe): wire silu_and_mul through C++ bridge in corex_moe.py

2026-08-10 06:36:40 +00:00

ex_loader.py

fix(EX): corex ivcore10 build flags + deploy pipeline + topk kernel cleanup

2026-08-10 02:31:55 +00:00

ix_bridge.py

fix(bridge): link against libixformer.so for silu_and_mul symbol

2026-08-10 06:29:11 +00:00

moe_topk.py

feat(EX): wire xllm CUB topk_softmax kernel into MoE routing

2026-08-10 03:10:58 +00:00

patch_model.py

refactor(EX): upstream-aligned kernels + FlashQLA GDN backend

2026-08-10 02:55:58 +00:00