0b0c47fddd
Sub 655 root causes (confirmed from log analysis): 1. protocol.py: max_completion_tokens never folded into max_tokens → 162/881 replay requests rejected 400 (extra_forbidden) 2. max_num_seqs=1 → t2_n_2 test fails (needs n=2) 3. max_model_len=131072 → OOM crash at 62% replay, opencompass all 0 Fixes: - protocol.py: model_validator fold_max_completion_tokens - yaml: max_num_seqs=2, max_model_len=80000, PYTORCH_CUDA_ALLOC_CONF - topk_softmax stays =0 (corex CUB BlockReduce incompatible on BI-V100) xllm_latest import to ex_engine/: - npu_torch layers: GDN(1164L), Qwen3.5 GDN, attention, fused_moe - cuda/moe kernels: topk_softmax_kernels.cuh, moe_combine, moe_compute_index - npu kernels: causal_conv1d, recurrent_gated_delta_rule - model headers: qwen3_5.h, qwen3_next.h
29 lines
504 B
Plaintext
29 lines
504 B
Plaintext
include(cc_library)
|
|
set(CMAKE_CUDA_ARCHITECTURES ivcore11)
|
|
file(GLOB_RECURSE ILU_HEADER_FILES
|
|
"${CMAKE_CURRENT_LIST_DIR}/*.h"
|
|
)
|
|
|
|
file(GLOB_RECURSE ILU_SOURCE_FILES
|
|
"${CMAKE_CURRENT_LIST_DIR}/*.cpp"
|
|
"${CMAKE_CURRENT_LIST_DIR}/*.cu"
|
|
)
|
|
|
|
find_package(Python3 REQUIRED COMPONENTS Interpreter Development)
|
|
|
|
cc_library(
|
|
NAME
|
|
ilu_kernels
|
|
HDRS
|
|
${ILU_HEADER_FILES}
|
|
SRCS
|
|
${ILU_SOURCE_FILES}
|
|
DEPS
|
|
torch
|
|
:util
|
|
ixformer_kernels
|
|
ixformer
|
|
${Python3_LIBRARIES}
|
|
cuinfer
|
|
)
|