prebuilt: 5 xllm CUDA kernel .so for BI-V100 (ivcore10)
All 12/12 AST call chain tests passed: xllm_norm.so (1.4MB) rms_norm max_err=0.000000, fused_add_rms_norm err=0.001953 xllm_activation.so (1.3MB) silu_and_mul err=0.001953, gelu_and_mul err=0.001953 xllm_rope.so (1.2MB) rotary_embedding q_diff=1360 k_diff=1404 xllm_cache.so (1.3MB) reshape_paged_cache err=0.000000 xllm_moe.so (?.?MB) fused_topk weight_sum_err<0.01, compute_index total=64, combine err<0.1 vs ixformer: rms_norm err=0.000000, silu_and_mul err=0.000000 Compiled with corex clang/16 --cuda-gpu-arch=ivcore10 Using corex CUB (/usr/local/corex/include/cub/), NOT CCCL 3.6
This commit is contained in:
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_activation.so
Executable file
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_activation.so
Executable file
Binary file not shown.
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_cache.so
Executable file
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_cache.so
Executable file
Binary file not shown.
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_moe.so
Executable file
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_moe.so
Executable file
Binary file not shown.
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_norm.so
Executable file
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_norm.so
Executable file
Binary file not shown.
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_rope.so
Executable file
BIN
qwen3_6_scripts/prebuilt/corex-3.2.3-ivcore10/xllm_rope.so
Executable file
Binary file not shown.
Reference in New Issue
Block a user