002f9879b2
Replaces cherry-picked upstream_ref with complete source trees. xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files) Complete: kernels → layers → models → runtime → scheduler → api Excluded: .git, binary images, third_party submodule checkouts ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files) Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops Excluded: tests, benchmarks, docs, examples (not needed for reference) Critical call chains now fully traceable: MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp Attention: ixformer.h → xllm_paged_attention → attention.cpp
22 lines
418 B
Python
22 lines
418 B
Python
import os
|
|
import platform
|
|
import subprocess
|
|
import sys
|
|
from typing import Dict
|
|
|
|
import xllm
|
|
|
|
|
|
def launch_xllm() -> int:
|
|
system = platform.system()
|
|
binary_name: str = {
|
|
"Linux": "xllm",
|
|
# "Windows"
|
|
# "Darwin"
|
|
}.get(system, "xllm")
|
|
|
|
bin_path: str = os.path.dirname(xllm.__file__) + "/xllm"
|
|
|
|
result = subprocess.run([str(bin_path)] + sys.argv[1:])
|
|
return result.returncode
|