llama-cpp-pascal
Pre-tensor-core (Pascal GTX 1070) inference optimizations for llama.cpp: native Turbo3 compressed-KV flash attention, PTQ1 ternary DP4A matmuls, chunked gated-delta-net, TurboQuant/VBR KV on 80K-262K contexts
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
GITHUB · launched Nov 9, 2026 · 15 upvotes (top 94%) · 0 views
Niche: llm inference engines · 133 launches, 4 in the last 7 days ▼ -33% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
- cuda
- flash-attention
- gtx1070
- kv-cache
- llama-cpp
- pascal
- +2 more
Visit website ↗ Source listing ↗
More like this: all 133 launches in llm inference engines →
Could you build this?
No The value is custom GPU kernels for flash attention, ternary matmuls and compressed KV caches tuned for Pascal hardware, which is specialized low-level CUDA and ML-systems research.
Competitors
Other products that read as similar to this one : 2421 launches clear the similarity bar, closest 8 shown.
Attention rank: #2258 of 2422 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 375 days after the earliest competitor.
- strixite · github · 2026-10-04 · 11 upvotes · similarity 0.66
- kindi · github · 2026-10-20 · 40 upvotes · similarity 0.65
- Ascend-H3 · github · 2026-10-30 · 29 upvotes · similarity 0.65
- Tiny-vLLM · hn · 2026-05-29 · 205 upvotes · similarity 0.63
- open_rknpu2_lm_infer · github · 2026-10-14 · 13 upvotes · similarity 0.62
- AbliteratedOutTheBox · github · 2026-10-21 · 120 upvotes · similarity 0.62
- LLamaTritLLM · github · 2026-09-11 · 10 upvotes · similarity 0.62
- llama.cpp-omni · github · 2026-10-13 · 20 upvotes · similarity 0.61
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.