HN Explorer

pythongiant

↗ HN profile [ 60.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Bodhan.ai releases 1.2B ASR model that covers 22 Indian Languages (bodhan.ai)
    1 points 0
  2. 1 points 0
  3. Show HN: Proxima serves 4x more requests with no hardware change on vLLM (github.com)

    hey everyone, i decided to make a vLLM plugin that implements the Star-KV paper. the results are quiet promising with a decode kernel thats faster than FA2 in higher batch sizes. would love any thoughts and…

    3 points 1
  4. 1 points 0
  5. Show HN: TurboQuant for mlx-lm (Apple Silicon) (github.com)

    Hi HN, I built mlx-turboquant, an implementation of Google's TurboQuant KV-cache compression algorithm for Apple's MLX framework. The repository includes quality benchmarks, memory benchmarks, and a modular…

    1 points 1
  6. Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT (pythongiant.github.io)
    20 points 18
  7. CUDA Programming: From Zero to GPU Kernels – A Beginner's Guide (pythongiant.github.io)
    1 points 1
  8. Show HN: I built GPT from scratch to understand how it works (pythongiant.github.io)

    If you’ve ever been curious about how GPT actually works under the hood, I built a small project you might find interesting. I implemented a GPT-style transformer from scratch in a single notebook—covering tokenization,…

    7 points 0