RahulSChand/gpu_poor
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
Language:JavaScript
Total stars: 878
Stars trend:
#javascript
#ggml, #gpu, #huggingface, #languagemodel, #llama, #llama2, #llamacpp, #llm, #pytorch, #quantization
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
Language:JavaScript
Total stars: 878
Stars trend:
5 Oct 2024
9am ▋ +5
10am ▏ +1
11am ▉ +7
12pm ▌ +4
1pm █▎ +10
2pm █▏ +9
3pm █▏ +9
4pm █▍ +11
5pm ▊ +6
6pm █▎ +10
7pm █▍ +11#javascript
#ggml, #gpu, #huggingface, #languagemodel, #llama, #llama2, #llamacpp, #llm, #pytorch, #quantization
kelindar/search
Go library for embedded vector search and semantic embeddings using llama.cpp
Language:Go
Total stars: 118
Stars trend:
#go
#ai, #bert, #embeddings, #gguf, #gpu, #llamacpp, #searchengine, #semanticsearch, #simd, #vectorsearch
Go library for embedded vector search and semantic embeddings using llama.cpp
Language:Go
Total stars: 118
Stars trend:
29 Oct 2024
10pm ▌ +4
11pm █▉ +15
30 Oct 2024
12am ██ +16
1am ██▊ +22
2am █▎ +10
3am █ +8#go
#ai, #bert, #embeddings, #gguf, #gpu, #llamacpp, #searchengine, #semanticsearch, #simd, #vectorsearch
taichi-dev/taichi
Productive, portable, and performant GPU programming in Python.
Language:C++
Total stars: 25721
Stars trend:
#cplusplus
#computergraphics, #differentiableprogramming, #gpu, #gpuprogramming, #sparsecomputation, #taichi
Productive, portable, and performant GPU programming in Python.
Language:C++
Total stars: 25721
Stars trend:
19 Dec 2024
1am ▎ +2
2am ▉ +7
3am ▎ +2
4am ▌ +4
5am ▉ +7
6am █▊ +14
7am █▏ +9
8am █ +8
9am █▏ +9
10am ▍ +3
11am █▌ +12
12pm ▌ +4#cplusplus
#computergraphics, #differentiableprogramming, #gpu, #gpuprogramming, #sparsecomputation, #taichi
kevmo314/scuda
SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
Language:C++
Total stars: 1118
Stars trend:
#cplusplus
#cublas, #cuda, #cudnn, #gpu, #mlops, #networking, #nvml, #remoteaccess
SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
Language:C++
Total stars: 1118
Stars trend:
13 Jan 2025
12pm █▉ +15
1pm █▎ +10
2pm █ +8
3pm █▎ +10
4pm █▊ +14
5pm ▉ +7
6pm ▍ +3
7pm █▏ +9
8pm ▉ +7
9pm ▌ +4
10pm ▋ +5
11pm ▊ +6#cplusplus
#cublas, #cuda, #cudnn, #gpu, #mlops, #networking, #nvml, #remoteaccess
Rust-GPU/Rust-CUDA
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
Language:Rust
Total stars: 4103
Stars trend:
#rust
#cuda, #cudakernels, #cudaprogramming, #gpgpu, #gpu, #gpuprogramming, #rust, #rustlang
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
Language:Rust
Total stars: 4103
Stars trend:
11 Apr 2025
5pm ██ +16
6pm █▋ +13
7pm ██▍ +19
8pm ██▍ +19
9pm █ +8#rust
#cuda, #cudakernels, #cudaprogramming, #gpgpu, #gpu, #gpuprogramming, #rust, #rustlang
skypilot-org/skypilot
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 16+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Language:Python
Total stars: 7844
Stars trend:
#python
#cloudcomputing, #cloudmanagement, #costmanagement, #costoptimization, #datascience, #deeplearning, #distributedtraining, #finops, #gpu, #hyperparametertuning, #jobqueue, #jobscheduler, #llmserving, #llmtraining, #machinelearning, #mlinfrastructure, #mlplatform, #multicloud, #spotinstances, #tpu
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 16+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Language:Python
Total stars: 7844
Stars trend:
26 Apr 2025
3pm █▍ +11
4pm █ +8
5pm ▍ +3
6pm ▉ +7
7pm ▉ +7
8pm █▍ +11
9pm ▊ +6
10pm ▍ +3
11pm ▍ +3
27 Apr 2025
12am ▎ +2
1am █▏ +9
2am █▍ +11#python
#cloudcomputing, #cloudmanagement, #costmanagement, #costoptimization, #datascience, #deeplearning, #distributedtraining, #finops, #gpu, #hyperparametertuning, #jobqueue, #jobscheduler, #llmserving, #llmtraining, #machinelearning, #mlinfrastructure, #mlplatform, #multicloud, #spotinstances, #tpu
LegNeato/rust-gpu-chimera
Demo project showing a single Rust codebase running on CPU and directly on GPUs
Language:Rust
Total stars: 154
Stars trend:
#rust
#cuda, #gpu, #rust, #rustcuda, #rustgpu, #vulkan
Demo project showing a single Rust codebase running on CPU and directly on GPUs
Language:Rust
Total stars: 154
Stars trend:
26 Jul 2025
6am ▏ +1
7am ▎ +2
8am ▍ +3
9am ▏ +1
10am █▏ +9
11am █▏ +9
12pm █▎ +10
1pm █▏ +9
2pm █▌ +12
3pm █▍ +11
4pm █▎ +10
5pm ▋ +5#rust
#cuda, #gpu, #rust, #rustcuda, #rustgpu, #vulkan
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python
Total stars: 94663
Stars trend:
#python
#autograd, #deeplearning, #gpu, #machinelearning, #neuralnetwork, #numpy, #python, #tensor
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python
Total stars: 94663
Stars trend:
3 Nov 2025
10pm ▍ +3
11pm ▏ +1
4 Nov 2025
12am ▍ +3
1am ▍ +3
2am ▉ +7
3am ▋ +5
4am ▋ +5
5am ▎ +2
6am ▌ +4
7am ▌ +4
8am +0
9am ▌ +4#python
#autograd, #deeplearning, #gpu, #machinelearning, #neuralnetwork, #numpy, #python, #tensor
software-mansion/TypeGPU
A modular and open-ended toolkit for WebGPU, with advanced type inference and the ability to write shaders in TypeScript
Language:TypeScript
Total stars: 1252
Stars trend:
#typescript
#gpgpu, #gpu, #gpucomputing, #gpuprogramming, #graphics, #javascript, #typesafe, #typescript, #webgpu, #webgpuapi, #wgsl, #wgslshader
A modular and open-ended toolkit for WebGPU, with advanced type inference and the ability to write shaders in TypeScript
Language:TypeScript
Total stars: 1252
Stars trend:
4 Nov 2025
9pm ▏ +1
10pm ▋ +5
11pm ▍ +3
5 Nov 2025
12am ▏ +1
1am ▍ +3
2am ▏ +1
3am ▍ +3
4am ▋ +5
5am ▎ +2
6am ▉ +7
7am ▌ +4
8am ▍ +3#typescript
#gpgpu, #gpu, #gpucomputing, #gpuprogramming, #graphics, #javascript, #typesafe, #typescript, #webgpu, #webgpuapi, #wgsl, #wgslshader
thu-pacman/chitu
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Language:Python
Total stars: 1877
Stars trend:
#python
#deepseek, #gpu, #llm, #llmserving, #modelserving, #pytorch
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Language:Python
Total stars: 1877
Stars trend:
12 Feb 2026
1am ▏ +1
2am ▎ +2
3am +0
4am ▊ +6
5am █ +8
6am █ +8
7am █▏ +9
8am ▉ +7
9am ▌ +4
10am █ +8
11am ▊ +6
12pm ▋ +5#python
#deepseek, #gpu, #llm, #llmserving, #modelserving, #pytorch
👍1
Zaneham/BarraCUDA
Open-source CUDA compiler targeting AMD GPUs (and more in the future!). Compiles .cu to GFX11 machine code.
Language:C
Total stars: 525
Stars trend:
#c
#c99, #compiler, #cuda, #gpu, #ml
Open-source CUDA compiler targeting AMD GPUs (and more in the future!). Compiles .cu to GFX11 machine code.
Language:C
Total stars: 525
Stars trend:
18 Feb 2026
12am █▉ +15
1am █▊ +14
2am █▏ +9
3am █▎ +10
4am █▎ +10
5am █▌ +12
6am █▎ +10
7am █▎ +10
8am ██▏ +17
9am ▉ +7
10am █ +8
11am █▎ +10#c
#c99, #compiler, #cuda, #gpu, #ml
livehl/aimirror
🚀 200倍速！AI时代的下载神器 | Docker/PyPI/HuggingFace/CRAN 全加速 | 并行分片+智能缓存，让下载飞起来
Language:Python
Total stars: 585
Stars trend:
#python
#aitools, #cacheproxy, #cuda, #deeplearning, #dockerregistry, #downloadaccelerator, #fastapi, #gpu, #huggingface, #largelanguagemodels, #llm, #machinelearning, #modeldownload, #paralleldownload, #pypimirror, #python, #pytorch, #tensorflow
🚀 200倍速！AI时代的下载神器 | Docker/PyPI/HuggingFace/CRAN 全加速 | 并行分片+智能缓存，让下载飞起来
Language:Python
Total stars: 585
Stars trend:
10 Mar 2026
5pm ▏ +1
6pm ▏ +1
7pm ▍ +3
8pm ▏ +1
9pm +0
10pm +0
11pm ▌ +4
11 Mar 2026
12am █▏ +9
1am ▉ +7
2am ▋ +5
3am ███▏ +25
4am ███▉ +31#python
#aitools, #cacheproxy, #cuda, #deeplearning, #dockerregistry, #downloadaccelerator, #fastapi, #gpu, #huggingface, #largelanguagemodels, #llm, #machinelearning, #modeldownload, #paralleldownload, #pypimirror, #python, #pytorch, #tensorflow
RightNow-AI/autokernel
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
Language:Python
Total stars: 206
Stars trend:
#python
#autoresearch, #cuda, #gpu, #kerneloptimization, #pytorch, #triton
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
Language:Python
Total stars: 206
Stars trend:
11 Mar 2026
2am ▏ +1
3am +0
4am +0
5am ▌ +4
6am ▍ +3
7am ▏ +1
8am ▍ +3
9am ▏ +1
10am ▌ +4
11am ▍ +3
12pm ▎ +2
1pm ▏ +1#python
#autoresearch, #cuda, #gpu, #kerneloptimization, #pytorch, #triton
peters/horizon
GPU-accelerated spatial terminal observatory — manage terminals, AI agents, and dev tools on an infinite canvas
Language:Rust
Total stars: 142
Stars trend:
#rust
#aiagents, #claude, #codex, #developertools, #egui, #gpu, #rust, #terminal, #terminalemulator, #wgpu
GPU-accelerated spatial terminal observatory — manage terminals, AI agents, and dev tools on an infinite canvas
Language:Rust
Total stars: 142
Stars trend:
17 Mar 2026
7pm ▏ +1
8pm ▎ +2
9pm ▏ +1
10pm ▋ +5
11pm █ +8
18 Mar 2026
12am ▌ +4
1am ▏ +1
2am +0
3am ▏ +1
4am ▌ +4#rust
#aiagents, #claude, #codex, #developertools, #egui, #gpu, #rust, #terminal, #terminalemulator, #wgpu
lemonade-sdk/lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
Language:C++
Total stars: 2902
Stars trend:
#cplusplus
#ai, #amd, #genai, #gpu, #llama, #llm, #llminference, #localserver, #mcp, #mcpserver, #mistral, #npu, #onnxruntime, #openaiapi, #qwen, #radeon, #rocm, #ryzen, #vulkan
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
Language:C++
Total stars: 2902
Stars trend:
2 Apr 2026
12pm ▋ +5
1pm ▋ +5
2pm ▋ +5
3pm ▎ +2
4pm ▎ +2
5pm ▎ +2
6pm ▉ +7
7pm ▍ +3#cplusplus
#ai, #amd, #genai, #gpu, #llama, #llm, #llminference, #localserver, #mcp, #mcpserver, #mistral, #npu, #onnxruntime, #openaiapi, #qwen, #radeon, #rocm, #ryzen, #vulkan
mayocream/koharu
ML-powered manga translator, written in Rust.
Language:Rust
Total stars: 2098
Stars trend:
#rust
#computervision, #deeplearning, #gpu, #japanese, #manga, #rust, #tauri
ML-powered manga translator, written in Rust.
Language:Rust
Total stars: 2098
Stars trend:
8 Apr 2026
7pm ▏ +1
8pm ▏ +1
9pm ▍ +3
10pm ▊ +6
11pm ▋ +5
9 Apr 2026
12am █ +8
1am ▌ +4#rust
#computervision, #deeplearning, #gpu, #japanese, #manga, #rust, #tauri
orhun/ratty
A GPU-rendered terminal emulator with inline 3D graphics 🐀🧀
Language:Rust
Total stars: 811
Stars trend:
#rust
#3d, #3dgraphics, #command, #gpu, #gpurendering, #graphics, #ratatui, #ratty, #rust, #templeos, #terminal, #terminalemulator, #terminalemulators, #terminalgraphics
A GPU-rendered terminal emulator with inline 3D graphics 🐀🧀
Language:Rust
Total stars: 811
Stars trend:
11 May 2026
10am ▍ +3
11am ▌ +4
12pm ▎ +2
1pm ▎ +2
2pm +0
3pm ▍ +3
4pm ▍ +3
5pm ▎ +2
6pm ▋ +5
7pm ▍ +3#rust
#3d, #3dgraphics, #command, #gpu, #gpurendering, #graphics, #ratatui, #ratty, #rust, #templeos, #terminal, #terminalemulator, #terminalemulators, #terminalgraphics
alternbits/awesome-cuda-books
A curated list of best cuda programming books
Language:
Total stars: 552
Stars trend:
#cpp, #cuda, #cudabasics, #cudabook, #cudacpp, #cudaprogramming, #cudatutorial, #gpu, #gpucomputing, #gpuoptimization, #gpuprogramming, #nvidia
A curated list of best cuda programming books
Language:
Total stars: 552
Stars trend:
17 May 2026
10pm ▍ +3
11pm ▍ +3
18 May 2026
12am ▎ +2
1am ▌ +4
2am ▋ +5
3am ▋ +5
4am ▌ +4
5am ▎ +2
6am ▏ +1
7am ▎ +2#cpp, #cuda, #cudabasics, #cudabook, #cudacpp, #cudaprogramming, #cudatutorial, #gpu, #gpucomputing, #gpuoptimization, #gpuprogramming, #nvidia