Claude 6425a96728 fix(runtime): bridge加载失败安全降级到Tier1(ixformer.functions) ...

根因：ixformer.h声明的是ixformer::infer::*命名空间，但base image
实际导出的是ixformer_torch_ext::*(in _ixformer_torch.so)和
ixformer::functions::*(in libixformer.so)。命名空间不匹配导致
bridge .so虽然编译成功但import时undefined symbol。

当前方案：bridge加载失败时安全降级到Tier1(ixformer.functions)，
这是base image的Python binding，底层调用同样的CUDA kernel，性能一致。
Tier1已有silu_and_mul/rms_norm/rotary_embedding/paged_attention等。

后续迭代：重写ixformer.h用正确的ixformer_torch_ext namespace。

2026-08-11 17:17:25 +00:00

..

__init__.py

fix(CRITICAL): docker build容错 + max_completion_tokens + extra=ignore + ix_unified bridge

2026-08-11 07:13:05 +00:00

corex_fa2.py

feat(CRITICAL): rewrite corex_gdn/moe/fa2 to use real ixformer dispatch

2026-08-11 03:49:41 +00:00

corex_gdn.py

feat(CRITICAL): rewrite corex_gdn/moe/fa2 to use real ixformer dispatch

2026-08-11 03:49:41 +00:00

corex_moe.py

feat(CRITICAL): rewrite corex_gdn/moe/fa2 to use real ixformer dispatch

2026-08-11 03:49:41 +00:00

corex_so_loader.py

fix(CRITICAL): merge 26e6cb40 build pipeline + HEAD features — fix docker build

2026-08-11 07:58:14 +00:00

ex_loader.py

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

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

ex_topk_bridge.py

feat: ex_factor_0.so ctypes桥接 + ex_engine package部署

2026-08-11 09:57:30 +00:00

gdn_fp32.py

fix(CRITICAL): docker build容错 + max_completion_tokens + extra=ignore + ix_unified bridge

2026-08-11 07:13:05 +00:00

ix_bridge.py

feat(SO): ix_moe_bridge.cpp — dlopen bridge for 12 ixformer::infer functions

2026-08-11 02:37:03 +00:00

ix_unified.py

fix(runtime): bridge加载失败安全降级到Tier1(ixformer.functions)

2026-08-11 17:17:25 +00:00

moe_dispatch.py

fix(CRITICAL): docker build容错 + max_completion_tokens + extra=ignore + ix_unified bridge

2026-08-11 07:13:05 +00:00

moe_fused_dispatch.py

fix(CRITICAL): merge 26e6cb40 build pipeline + HEAD features — fix docker build

2026-08-11 07:58:14 +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