Search: github.com/vraa | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: Recurser lib reduces GPT2-XL VRAM usage by 25% and runs it on Colab (github.com/max-ng)

5 points

3 years ago

62.

Show HN: A Vaadin Algebra and Calculus Solver Built with AI Assistance

4 points

3 months ago

63.

Show HN: AudioGhost AI – Run Meta's Sam-Audio on Consumer GPUs (4GB-6GB VRAM) (github.com/0x0funky)

3 points

5 months ago

64.

Shimmy v1.7.0: Running 42B Moe Models on Consumer GPUs with 99.9% VRAM Reduction (github.com/Michael-A-Kuykendall)

3 points

8 months ago

65.

Grinder12: 0.96-Bit Lossless Streaming KV-Cache (16.55x VRAM Savings (github.com/ggml-org)

3 points

a month ago

66.

Show HN: L88 – A Local RAG System on 8GB VRAM (Need Architecture Feedback) (github.com/Hundred-Trillion)

3 points

3 months ago

67.

Unsloth – Train LLMs 2x faster with 70% less VRAM (github.com/unslothai)

3 points

6 months ago

68.

Quansloth Using Google's Turboquant Breaks the "VRAM Wall" for Local LLMs (github.com/PacifAIst)

2 points

2 months ago

69.

Show HN: I built a <400ms latency voice agent that runs on a 4gb vram GTX 1650" (github.com/pheonix-delta)

2 points

4 months ago

70.

Show HN: A Vaadin 24, Spring algebra calculator with dynamic variable buttons

2 points

6 months ago

71.

Dead Simple Web UI for Training Flux LoRA with Low VRAM (12GB/16GB/20GB) Support (github.com/cocktailpeanut)

2 points

2 years ago

72.

Show HN: Parakeet LLM Demo (378M param. 8GB VRAM)

2 points

2 years ago

73.

Adjust VRAM/RAM Split on Apple Silicon (github.com/ggerganov)

1 point

3 years ago

74.

VDPAU-to-VAAPI accelerates Flash video on Intel GFX (github.com/i-rinat)

1 point

13 years ago

75.

2.3x KV Cache Compression at 32k Context – Cut VRAM Costs by 50% (github.com/Jamie2111)

1 point

21 days ago

76.

Show HN: VAAK (Voice-Activated Autonomous-Knowledge-System) (github.com/ayushmaanbhav)

1 point

5 months ago

77.

Show HN: QKV Core – Run 7B LLMs on 4GB VRAM via surgical memory alignment (github.com/QKV-Core)

1 point

6 months ago

78.

Super Merryo Trolls: An Adventure from the Days Before VRAM (github.com/GBirkel)

1 point

2 years ago

79.

Rust Wishlist: functions with keyword args, default args, varargs (github.com/rust-lang)

1 point

6 years ago

80.

Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (github.com/antoinezambelli)

687 points

17 days ago

81.

Show HN: InvokeAI, an open source Stable Diffusion toolkit and WebUI (github.com/invoke-ai)

414 points

4 years ago

82.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training (github.com/alainnothere)

265 points

3 months ago

83.

Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformers

189 points

2 years ago

84.

Tell HN: Please Stop Using Imgur

69 points

4 years ago

85.

Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts (github.com/Zyora-Dev)

58 points

3 months ago

86.

Show HN: I built a RISC-V emulator that runs DOOM (github.com/lalitshankarch)

50 points

a month ago

87.

Show HN: Local task classifier and dispatcher on RTX 3080 (github.com/resilientworkflowsentinel)

26 points

4 months ago

88.

Show HN: KTransformers–236B Model and 1M Context LLM Inference on Local Machines (github.com/kvcache-ai)

20 points

2 years ago

89.

Show HN: Demon – open-source real-time music diffusion engine, 25Hz local GPU (daydreamlive.github.io)

17 points

ryanontheinside

8 days ago

90.

Show HN: Finetune Llama-3.1 2x faster in a Colab (colab.research.google.com)

16 points

2 years ago