Claude 2b12fe687e feat: hgemm_warptiling.cu — siboehm kernel 10 ported to WARPSIZE=64 FP16 ...

1:1 from upstream_ref/sgemm_cuda/10_kernel_warptiling.cuh.
3 changes: WARPSIZE 32→64, float→__half, FP32 accumulator.

Launch config (confirmed by probe_warp64.sh):
  NUM_THREADS=128, 2 warps of 64
  BM=128 BN=128 BK=16 WM=64 WN=128 WNITER=4 TM=4 TN=4
  WMITER=2, WSUBM=32, WSUBN=32, threads_per_warp=64 ✓

2026-08-14 17:05:59 +00:00

..

csrc

feat: moe_expert_gemm.cpp — C++ loop over experts via ixformer_linear (replaces Python for-loop)

2026-08-14 12:09:50 +00:00

fla_kernels

feat: import CUDA kernels from xllm/CCCL/FLA upstream repos

2026-08-14 07:48:52 +00:00

include

fix(CRITICAL): engine death on image request + stop overwriting base corex modules

2026-08-10 09:12:05 +00:00

python

fix(build): match project_7 proven Dockerfile — remove ENV lines + .dockerignore

2026-08-13 02:48:28 +00:00

xllm_kernels

feat: hgemm_warptiling.cu — siboehm kernel 10 ported to WARPSIZE=64 FP16

2026-08-14 17:05:59 +00:00

xllm_layers

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

xllm_models

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

build.sh

fix(build): 回退qwen3_6_scripts+ex_engine到26e6cb40(能得分版本)

2026-08-12 01:33:24 +00:00

deploy_corex_modules.sh

feat(EX): corex_fa2.py — third dlopen module from comp 168 AST chain

2026-08-10 04:01:21 +00:00

precompile_moe_kernels.py

fix(build): 回退qwen3_6_scripts+ex_engine到26e6cb40(能得分版本)

2026-08-12 01:33:24 +00:00

precompile_moe_topk.py

fix(MoE): robust CUDA kernel loading + no-GPU precompile

2026-08-10 07:50:28 +00:00