Search: github.com/qvl | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

631.

Show HN: PDF2MD – Rust+Redis+ClickHouse+VLLM conversion pipeline for PDFs

github.com/devflowinc

2 years ago

13 points

632.

Show HN: LoongForge-A high-performance training framework for LLM, VLM, VLA, Wan

github.com/baidu-baige

a month ago

10 points

633.

Show HN: Cursed Browser – a VLM reads the HTML and hallucinates the page

github.com/scosman

a month ago

7 points

634.

Show HN: Docker Model Runner Integrates vLLM for High-Throughput Inference

github.com/docker

7 months ago

7 points

635.

Ask HN: What do language designers think of VLang?

7 years ago

6 points

636.

Show HN: SupaVlog – a vlog application starter kit

github.com/hookdeck

2 years ago

6 points

637.

Show HN: Llmtop – Htop for LLM Inference Clusters (vLLM, SGLang, Ollama, llama)

github.com/InfraWhisperer

3 months ago

5 points

638.

Qwen 3.6 93B with MTP on 2×RTX 3090 NVLink=187 tokens/SEC,LLM lost bleat-a-thon

github.com/Augmented-Reality-Virtual-Reality-AR-VR

11 days ago

4 points

639.

Show HN: Harbor v0.4.19 – harbor launch –back end vLLM –web codex

a month ago

4 points

640.

Cursed_browser: Web browser with a VLM as rendering engine

github.com/scosman

2 months ago

4 points

641.

Novofetch: A fast minimalist system fetch tool written in Vlang

github.com/yehorovye

a year ago

4 points

642.

Tinyvvm – a simple window manager written in vlang

github.com/Eliyaan

2 years ago

4 points

643.

When AI Beats Us in Every Test We Can Do: A Simple Definition for Human-Lvl AGI

github.com/mrconter1

2 years ago

3 points

644.

SketchVLM: Letting VLMs draw on images while explaining their reasoning

github.com/Brandon-Collins7

2 months ago

3 points

645.

Self-Host LLMs with VLLM and BentoML

github.com/bentoml

2 years ago

3 points

646.

DVL: a language and compiler for writing numerical kernels

github.com/axch

13 years ago

3 points

647.

Profile(v2.1.4) physics-aware optimizer for vLLM (31→470 tok/s on A100)

github.com/jungledesh

6 days ago

3 points

648.

Show HN: Local video search with Qwen3-VL: no API, runs on Apple Silicon, GPUs

github.com/ssrajadh

3 months ago

3 points

649.

Snow HN: ~950 line inference engine, on par with vLLM

github.com/naklecha

6 months ago

3 points

650.

Open source x 3: GRPO training with OpenEnv, vLLM, and Oumi

github.com/oumi-ai

7 months ago

3 points

651.

Show HN: Unsiloed Chunker – VLM powered semantic chunking for RAG

github.com/Unsiloed-AI

a year ago

3 points

652.

github.com/elliotchance

a year ago

3 points

653.

SDB Scans the Ruby Stack Without the GVL

github.com/yfractal

a year ago

3 points

654.

p-Vex: A Reconfigurable and Extensible [FPGA, 32-Bit] VLIW Soft Processor (VHDL)

github.com/tvanas

7 years ago

peter_d_sherman

3 points

655.

Deep Learning Toolkit-Enabled GPU Acceleration for Modern VLSI Placement

github.com/limbo018

7 years ago

3 points

656.

Show HN: High performance async web framework built with uvloop and httptools

github.com/gaojiuli

8 years ago

3 points

657.

VLA learns how to act. S2S decides whether the motion is physically trustworthy

github.com/timbo4u1

3 months ago

2 points

658.

Show HN: A single CLI to manage llama.cpp/vLLM/Ollama models

3 months ago

2 points

659.

Show HN: Fixxer – Local TUI to cull/organize RAW photos(CLIP, Qwen2.5-VL, rawpy)

github.com/BandwagonVibes

7 months ago

2 points

660.

Tiny-Qwen: Minimal PyTorch Re-Implementation of Qwen3 and Qwen2.5-VL

github.com/Emericen

10 months ago

2 points