tspeterkim/flash-attention-minimal
Flash Attention in ~100 lines of CUDA (forward pass only)
Language:Cuda
Total stars: 133
Stars trend:
#cuda
Flash Attention in ~100 lines of CUDA (forward pass only)
Language:Cuda
Total stars: 133
Stars trend:
16 Mar 2024
3pm ▋ +5
4pm ██▍ +19
5pm ███▎ +26
6pm █ +8
7pm ██ +16
8pm ▋ +5#cuda
HazyResearch/ThunderKittens
Tile primitives for speedy kernels
Language:Cuda
Total stars: 87
Stars trend:
#cuda
Tile primitives for speedy kernels
Language:Cuda
Total stars: 87
Stars trend:
12 May 2024
8pm █▌ +12
9pm ██▋ +21
10pm ██▋ +21
11pm ██▊ +22#cuda
beam-cloud/beta9
The open-source serverless GPU container runtime.
Language:Go
Total stars: 82
Stars trend:
#go
#cuda, #distributedcomputing, #finetuning, #generativeai, #gpu, #largelanguagemodels, #llm, #llminference, #mlplatform, #selfhosted
The open-source serverless GPU container runtime.
Language:Go
Total stars: 82
Stars trend:
13 May 2024
5pm █▎ +10
6pm ███▎ +26
7pm ██▋ +21
8pm ▉ +7
9pm ▊ +6
10pm █▍ +11#go
#cuda, #distributedcomputing, #finetuning, #generativeai, #gpu, #largelanguagemodels, #llm, #llminference, #mlplatform, #selfhosted
HigherOrderCO/HVM
A massively parallel, optimal functional runtime in Rust
Language:Cuda
Total stars: 7284
Stars trend:
#cuda
A massively parallel, optimal functional runtime in Rust
Language:Cuda
Total stars: 7284
Stars trend:
16 May 2024
4pm ▏ +1
5pm +0
6pm ▏ +1
7pm +0
8pm +0
9pm █▌ +12
10pm █▊ +14
11pm █▋ +13
17 May 2024
12am █▏ +9
1am █▍ +11
2am ▉ +7
3am █▎ +10#cuda
m4rs-mt/ILGPU
ILGPU JIT Compiler for high-performance .Net GPU programs
Language:C#
Total stars: 1156
Stars trend:
#csharp
#amd, #cil, #compiler, #cpu, #cuda, #dotnet, #gpgpu, #gpgpucomputing, #gpu, #ilgpu, #intel, #jit, #kernels, #msil, #nvidia, #opencl, #parallel, #ptx
ILGPU JIT Compiler for high-performance .Net GPU programs
Language:C#
Total stars: 1156
Stars trend:
17 May 2024
8pm ▏ +1
9pm ▏ +1
10pm ██▍ +19
11pm █▉ +15
18 May 2024
12am ▉ +7
1am ▊ +6
2am ▉ +7
3am █▎ +10
4am ▍ +3
5am █ +8#csharp
#amd, #cil, #compiler, #cpu, #cuda, #dotnet, #gpgpu, #gpgpucomputing, #gpu, #ilgpu, #intel, #jit, #kernels, #msil, #nvidia, #opencl, #parallel, #ptx
rapidsai/cudf
cuDF - GPU DataFrame Library
Language:C++
Total stars: 7615
Stars trend:
#cplusplus
#arrow, #cpp, #cuda, #cudf, #dask, #dataanalysis, #datascience, #dataframe, #gpu, #pandas, #pydata, #python, #rapids
cuDF - GPU DataFrame Library
Language:C++
Total stars: 7615
Stars trend:
2 Jun 2024
7pm ▎ +2
8pm ▋ +5
9pm +0
10pm +0
11pm █▍ +11
3 Jun 2024
12am █▏ +9
1am ██ +16
2am █▌ +12
3am █▋ +13
4am ██▌ +20#cplusplus
#arrow, #cpp, #cuda, #cudf, #dask, #dataanalysis, #datascience, #dataframe, #gpu, #pandas, #pydata, #python, #rapids
likejazz/llama3.cuda
llama3.cuda is a pure C/CUDA implementation for Llama 3 model.
Language:Cuda
Total stars: 89
Stars trend:
#cuda
llama3.cuda is a pure C/CUDA implementation for Llama 3 model.
Language:Cuda
Total stars: 89
Stars trend:
2 Jun 2024
11pm ▊ +6
3 Jun 2024
12am █▍ +11
1am █▌ +12
2am ▋ +5
3am ▌ +4
4am ▋ +5
5am ▌ +4
6am ▊ +6
7am █▏ +9
8am █▎ +10
9am █ +8#cuda
clu0/unet.cu
UNet diffusion model in pure CUDA
Language:Cuda
Total stars: 109
Stars trend:
#cuda
UNet diffusion model in pure CUDA
Language:Cuda
Total stars: 109
Stars trend:
28 Jun 2024
7pm ███▋ +29
8pm ████ +32
9pm █▉ +15
10pm █▎ +10
11pm █▏ +9
29 Jun 2024
12am █▏ +9#cuda