Search: github.com/vraa | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: L88 – A Local RAG System on 8GB VRAM (Need Architecture Feedback)

4 months ago

12 points

62.

Helios: 14B open source video model, real time at 19.5fps, runs on 6GB VRAM

github.com/PKU-YuanGroup

3 months ago

6 points

63.

Show HN: Recurser lib reduces GPT2-XL VRAM usage by 25% and runs it on Colab

github.com/max-ng

3 years ago

5 points

64.

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

4 months ago

4 points

65.

Show HN: AudioGhost AI – Run Meta's Sam-Audio on Consumer GPUs (4GB-6GB VRAM)

github.com/0x0funky

6 months ago

3 points

66.

Shimmy v1.7.0: Running 42B Moe Models on Consumer GPUs with 99.9% VRAM Reduction

github.com/Michael-A-Kuykendall

8 months ago

3 points

67.

Grinder12: 0.96-Bit Lossless Streaming KV-Cache (16.55x VRAM Savings

github.com/ggml-org

a month ago

3 points

68.

Show HN: L88 – A Local RAG System on 8GB VRAM (Need Architecture Feedback)

github.com/Hundred-Trillion

4 months ago

3 points

69.

Unsloth – Train LLMs 2x faster with 70% less VRAM

github.com/unslothai

6 months ago

3 points

70.

Quansloth Using Google's Turboquant Breaks the "VRAM Wall" for Local LLMs

github.com/PacifAIst

2 months ago

2 points

71.

Show HN: I built a <400ms latency voice agent that runs on a 4gb vram GTX 1650"

github.com/pheonix-delta

4 months ago

2 points

72.

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

7 months ago

2 points

73.

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

github.com/cocktailpeanut

2 years ago

2 points

74.

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

2 years ago

2 points

75.

Adjust VRAM/RAM Split on Apple Silicon

github.com/ggerganov

3 years ago

1 points

76.

VDPAU-to-VAAPI accelerates Flash video on Intel GFX

github.com/i-rinat

13 years ago

1 points

77.

2.3x KV Cache Compression at 32k Context – Cut VRAM Costs by 50%

github.com/Jamie2111

a month ago

1 points

78.

Show HN: VAAK (Voice-Activated Autonomous-Knowledge-System)

github.com/ayushmaanbhav

5 months ago

1 points

79.

Show HN: QKV Core – Run 7B LLMs on 4GB VRAM via surgical memory alignment

github.com/QKV-Core

6 months ago

1 points

80.

Super Merryo Trolls: An Adventure from the Days Before VRAM

github.com/GBirkel

2 years ago

1 points

81.

Rust Wishlist: functions with keyword args, default args, varargs

github.com/rust-lang

6 years ago

1 points

82.

Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks

github.com/antoinezambelli

a month ago

687 points

83.

Show HN: InvokeAI, an open source Stable Diffusion toolkit and WebUI

github.com/invoke-ai

4 years ago

414 points

84.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training

github.com/alainnothere

3 months ago

265 points

85.

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

2 years ago

189 points

86.

Tell HN: Please Stop Using Imgur

4 years ago

69 points

87.

Launch HN: General Instinct (YC P26) – Frontier models on edge devices

17 days ago

63 points

88.

Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts

github.com/Zyora-Dev

4 months ago

58 points

89.

Show HN: I built a RISC-V emulator that runs DOOM

github.com/lalitshankarch

2 months ago

50 points

90.

Show HN: Local task classifier and dispatcher on RTX 3080

github.com/resilientworkflowsentinel

5 months ago

26 points