Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Opt
Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads. We present Atrex-Bench, a benchmark whose 30 operators and 440 shapes are sampled directly from full-cluster pro
https://arxiv.org/abs/2607.14541v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
llm
Overlap with sectors you care about
Geography
Outside
Outside your target regions — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
L
Lingyun Yang
1.0
low confidence
Y
Yuxiao Wang
2.0
low confidence
S
Shenghao Liang
2.0
low confidence
L
Linfeng Yang
1.0
low confidence
D
Daocheng Ying
2.0
low confidence
C
Chunbo You
2.0
low confidence
R
Rui Zhang
2.0
low confidence
L
Luping Wang
2.0
low confidence
Y
Yinghao Yu
HK
2.0
low confidence
G
Guodong Yang
2.0
low confidence
L
Liping Zhang
2.0
low confidence
L
L Yang
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Trainy
· Active
Infrastructure for managing GPU clusters for training/serving.
founders not scraped yet