Search: github.com/l4l | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

331.

Show HN: LlamaExtract, a tool to automatically extract schema from documents (github.com/run-llama)

8 points

2 years ago

332.

Show HN: LLMdantic: Structured Output Is All You Need (github.com/firattamur)

8 points

2 years ago

333.

Show HN: Llm-benchmark – Benchmarks LLM-optimized code across multiple providers (github.com/thomasdavis)

8 points

thomasfromcdnjs

a year ago

334.

Show HN: LLVM-jutsu: Anti-LLM obfuscation pass (github.com/thebabush)

8 points

5 months ago

335.

Show HN: One-liner CLI for batched PDF-to-Markdown at $1 per ~6k pages (github.com/altaidevorg)

8 points

a year ago

336.

Llama2.c64: a port of llama2.c to the Commodore C64 (github.com/ytmytm)

8 points

a year ago

337.

Llama 3.1: 405B, the largest openly available model released (github.com/meta-llama)

8 points

2 years ago

338.

gg: "M2 Ultra is the absolute best personal LLM inference node you can buy." (github.com/ggerganov)

8 points

3 years ago

339.

LLaMA-rs: a Rust port of llama.cpp for fast LLaMA inference on CPU (github.com/setzer22)

8 points

3 years ago

340.

Enable fast sqrtss/sqrtps tuning for AMD Zen cores (github.com/llvm)

8 points

4 years ago

341.

LLVM-MOS: a project to port the LLVM toolkit to the MOS 6502 (github.com/llvm-mos)

8 points

5 years ago

342.

Show HN: LLM Wiki Compiler Inspired by Karpathy (github.com/atomicmemory)

7 points

2 months ago

343.

LLMZip: Lossless Text Compression Using Large Language Models (github.com/vcskaushik)

7 points

3 years ago

344.

Show HN: LLMStack – Self-Hosted, Low-Code Platform to Build AI Experiences (github.com/trypromptly)

7 points

3 years ago

345.

Apple is adding Mach-O's riscv32 support to LLVM (github.com/llvm)

7 points

a year ago

346.

Llama2 + Haystack on Colab (github.com/anakin87)

7 points

3 years ago

347.

Show HN: Llamero – A GUI app to easily download, install and infer LLaMA models (github.com/mpociot)

7 points

3 years ago

348.

Show HN: LLM Prompt Diff- Semantic Git Style Diffing for Prompts with Embeddings (github.com/aatakansalar)

7 points

a year ago

349.

Ggml 2x WASM Speed with SIMD Optimization Using 99% DeekSeek-R1-Generated Code (github.com/ggerganov)

7 points

a year ago

350.

Llama as a System (github.com/meta-llama)

7 points

2 years ago

351.

Distributed LLama3 Inference (github.com/evilsocket)

7 points

2 years ago

352.

Llama.cpp Working on Support for Llama3 (github.com/ggerganov)

7 points

2 years ago

353.

Show HN: secinsights.ai – An open-source full-stack app using LlamaIndex (github.com/run-llama)

7 points

3 years ago

354.

Show HN: LLMStack – Low-Code Platform for Building LLM Apps with LocalAI Support (github.com/trypromptly)

7 points

3 years ago

355.

Karpathy's llama2.c ported to pure Python (github.com/tairov)

6 points

3 years ago

356.

DeepSeek-R1 speeds up llama.cpp code by x2 (github.com/ggerganov)

6 points

a year ago

357.

Show HN: Llm.report – Open-source logging and analytics for OpenAI (github.com/dillionverma)

6 points

3 years ago

358.

L2E llama2.c running in a PDF in a Shroedinger PNG [pdf] (github.com/trholding)

6 points

a year ago

359.

Show HN: LlaMaKey – One master key for all cloud LLM/GenAI APIs (github.com/TexteaInc)

6 points

2 years ago

360.

Show HN: Llm.f90 fast, hackable transformer implementation in Fortran (github.com/rbitr)

6 points

3 years ago