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
31 lines
850 B
Python
31 lines
850 B
Python
# python examples/generate_embedding.py --model='/path/models/Qwen3-8B' --devices='npu:0' --runner pooling
|
|
# python generate_embedding.py --model='/path/models/Qwen3-8B' --devices='npu:0,npu:1'
|
|
|
|
from xllm import ArgumentParser, LLM, PoolingParams
|
|
|
|
# Create an embedding LLM.
|
|
parser = ArgumentParser()
|
|
args = parser.parse_args()
|
|
llm = LLM(**vars(args))
|
|
|
|
# Create pooling params.
|
|
pooling_params = PoolingParams()
|
|
|
|
inputs = [
|
|
"Hello, my name is",
|
|
"The president of the United States is",
|
|
"The capital of France is",
|
|
"The future of AI is",
|
|
]
|
|
|
|
outputs = llm.embed(inputs, pooling_params=pooling_params)
|
|
|
|
# Print the outputs.
|
|
for i, output in enumerate(outputs):
|
|
input_str = output.prompt
|
|
generated_embedding = output.outputs.embedding
|
|
print(f"Input: {input_str!r}, Generated embedding: {generated_embedding!r}")
|
|
|
|
llm.finish()
|
|
|