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
790 B
Python
30 lines
790 B
Python
# python examples/beam_search.py --model='/path/models/Qwen2-7B-Instruct' --devices='npu:0'
|
|
# python beam_search.py --model='/path/models/Qwen2-7B-Instruct' --devices='npu:0,npu:1'
|
|
|
|
from xllm import ArgumentParser, BeamSearchParams, LLM
|
|
|
|
# Create an LLM.
|
|
parser = ArgumentParser()
|
|
llm = LLM(**vars(parser.parse_args()))
|
|
|
|
beam_search_params = BeamSearchParams(
|
|
beam_width=2,
|
|
max_tokens=20,
|
|
)
|
|
|
|
outputs = llm.beam_search(
|
|
[
|
|
{"prompt": "Hello, my name is "},
|
|
{"prompt": "The president of the United States is "},
|
|
{"prompt": "The capital of France is "},
|
|
{"prompt": "The future of AI is "}
|
|
],
|
|
params=beam_search_params,
|
|
)
|
|
|
|
for output in outputs:
|
|
generated_text = output.sequences[0].text
|
|
print(f"Generated text: {generated_text!r}")
|
|
|
|
llm.finish()
|