DeepSelect
DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers
Details
- External ID
- 1362805626
- Source
- GITHUB
- Company
- —
- Product
- DeepSelect
- Website domain
- github.com
- Launched
- Sept. 9, 2026
- Cohort
- —
- Upvotes
- 327
- Upvotes percentile
- 0.9795029464514476
- Tags
- —
- Fetched at
- Sept. 13, 2026, 5:56 p.m.
- Updated at
- Sept. 13, 2026, 5:56 p.m.
Enrichment
- Theme
- ai video generation and editing tools
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- top-k kernels for deepseek sparse attention
- Manually corrected
- False
Could you build this?
No Developing custom TopK GPU kernels for Sparse Attention architectures requires deep low-level CUDA, Triton, and hardware-specific GPU memory hierarchy optimization.
What it would actually take: The project requires writing optimized CUDA, CUTLASS, or Triton kernels tailored to modern GPU architectures (e.g., Hopper/Blackwell) for TopK selection and sparse attention computation. It demands expertise in warp-level primitives, shared memory bank conflicts, tensor cores, and PyTorch C++ extension bindings to match peak hardware FLOPs and memory bandwidth.
Competitors
Other products that read as similar to this one — 976 launches clear the similarity bar, closest 8 shown.
Attention rank: #24 of 977 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 314 days after the earliest competitor.
- Simple-Attention-Sparsification · github · 2026-09-10 · 48 upvotes · similarity 0.64
- djev-dev · github · 2026-09-19 · 142 upvotes · similarity 0.56
- dsh-jev · github · 2026-09-19 · 18 upvotes · similarity 0.55
- genpark-singular-value-decomposition-svd-truncated-skill · github · 2026-09-28 · 7 upvotes · similarity 0.55
- DeepSeek-V4 Latent Reasoning · hn · 2026-08-09 · 30 upvotes · similarity 0.55
- genpark-vector-similarity-exact-and-topk-heap-selector-skill · github · 2026-09-29 · 7 upvotes · similarity 0.54
- Marlin-2B: a tiny VLM to extract structured information from videos · hn · 2026-05-18 · 7 upvotes · similarity 0.54
- Open-source AMDGCN kernels for optimizing LLM inference · hn · 2026-08-25 · 5 upvotes · similarity 0.54
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.