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
30 lines
624 B
Bash
30 lines
624 B
Bash
#!/bin/bash
|
|
set -e
|
|
|
|
function error() {
|
|
echo "Require build command, e.g. python setup.py build --device cuda"
|
|
exit 1
|
|
}
|
|
|
|
IMAGE="quay.io/jd_xllm/xllm-ai:xllm-dev-cuda-x86"
|
|
|
|
RUN_OPTS=(
|
|
--rm
|
|
-t
|
|
--privileged
|
|
--ipc=host
|
|
--network=host
|
|
--pid=host
|
|
--shm-size '128gb'
|
|
-v /export/home:/export/home
|
|
-v /export/home/cuda_vcpkg_cache:/root/.cache/vcpkg # cached vcpkg installed dir
|
|
-w /export/home
|
|
)
|
|
|
|
CMD="$*"
|
|
[[ -z "${CMD}" ]] && error
|
|
|
|
[[ ! -x $(command -v docker) ]] && echo "ERROR: 'docker' command is missing." && exit 1
|
|
|
|
docker run "${RUN_OPTS[@]}" "${IMAGE}" bash -c "set -euo pipefail; cd $(pwd); ${CMD}"
|