claude 0359103b9b fix: remove glog/cuda_ops_api.h dependency from all xllm CUDA kernels ...

cuda_ops_api.h includes glog/logging.h and ATen/DynamicLibrary.h
which are not available in corex standalone compilation.

All kernel .cu files only need device_utils.cuh (provides namespace,
XLLM_KERNEL_ATTR macro, CUB includes, type helpers).

Fixed files:
  norm.cu, activation.cu, rope.cu, block_copy.cu, reshape_paged_cache.cu
  moe/moe_combine.cu, moe/moe_compute_index.cu, moe/moe_fused_topk.cu

2026-08-14 10:30:10 +00:00

..

fused_moe.cpp

fix(critical): fold max_completion_tokens + max_num_seqs=2 + max_model_len=80000 + xllm_latest layer import

2026-08-13 03:19:39 +00:00

moe_combine.cu

fix: remove glog/cuda_ops_api.h dependency from all xllm CUDA kernels

2026-08-14 10:30:10 +00:00

moe_compute_index.cu

fix: remove glog/cuda_ops_api.h dependency from all xllm CUDA kernels

2026-08-14 10:30:10 +00:00

moe_fused_topk.cu

fix: remove glog/cuda_ops_api.h dependency from all xllm CUDA kernels

2026-08-14 10:30:10 +00:00

moe_topk_sigmoid_kernels.cuh

fix(critical): fold max_completion_tokens + max_num_seqs=2 + max_model_len=80000 + xllm_latest layer import

2026-08-13 03:19:39 +00:00

moe_topk_softmax_kernels.cuh

fix(critical): fold max_completion_tokens + max_num_seqs=2 + max_model_len=80000 + xllm_latest layer import

2026-08-13 03:19:39 +00:00

moe_topk.cuh

fix(critical): fold max_completion_tokens + max_num_seqs=2 + max_model_len=80000 + xllm_latest layer import

2026-08-13 03:19:39 +00:00