#Tpu

Showing 20 of 20 repositories tagged #tpu, ranked by stars

vllm-project
vllm-project
vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Score
100
★ 85.9k ⑂ 19.2k +30/day
Python
tensorflow
tensorflow
tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Score
33
★ 17.4k ⑂ 3.8k +7/day
Python
skypilot-org
skypilot-org
skypilot

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

Score
67
★ 10.3k ⑂ 1.1k +4/day
Python
tensorflow
tensorflow
adanet

Fast and flexible AutoML with learning guarantees.

Score
0
★ 3.5k ⑂ 525
Jupyter Notebook
hollance
hollance
neural-engine

Everything we actually know about the Apple Neural Engine (ANE)

Score
0
★ 2.5k ⑂ 97 +1/day
dphnAI
dphnAI
sonar

Large-scale LLM inference engine

Score
100
★ 1.8k ⑂ 202 +1/day
C++
sophgo
sophgo
tpu-mlir

Machine learning compiler based on MLIR for Sophgo TPU.

Score
100
★ 947 ⑂ 224 +5/day
C++
LuxDL
LuxDL
Lux.jl

Elegant and Performant Deep Learning

Score
88
★ 716 ⑂ 86 +2/day
Julia
tumaer
tumaer
JAXFLUIDS

Differentiable Fluid Dynamics Package

Score
75
★ 599 ⑂ 110 +2/day
Python
ayaka14732
ayaka14732
tpu-starter

Everything you want to know about Google Cloud TPU

Score
62
★ 571 ⑂ 30 +1/day
Python
AI-Hypercomputer
AI-Hypercomputer
JetStream

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

Score
50
★ 451 ⑂ 66 +3/day
Python
cameronshinn
cameronshinn
tiny-tpu

Small-scale Tensor Processing Unit built on an FPGA

Score
38
★ 228 ⑂ 29
Verilog
rickiepark
rickiepark
deep-learning-with-python-2nd

<케라스 창시자에게 배우는 딥러닝 2판> 도서의 코드 저장소

Score
25
★ 85 ⑂ 97
Jupyter Notebook
AI-Hypercomputer
AI-Hypercomputer
jetstream-pytorch

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"

Score
0
★ 85 ⑂ 21 +1/day
Python
wmcnally
wmcnally
evopose2d

EvoPose2D is a two-stage human pose estimation model that was designed using neuroevolution. It achieves state-of-the-art accuracy on COCO.

Score
12
★ 83 ⑂ 10
Python
lmvdz
lmvdz
solana-tpu-client

Solana TpuClient Typescript Implementation

Score
100
★ 69 ⑂ 28
TypeScript
RightNow-AI
RightNow-AI
tiny-tpu

Minimal TPU implementation with 8x8 systolic array and PyTorch integration

Score
50
★ 63 ⑂ 5
Python
trustless-engineering
trustless-engineering
leader-stream

Solana Leader TPU List and Event Stream

Score
50
★ 35 ⑂ 6
Rust
UofT-EcoSystem
UofT-EcoSystem
hfta

Boost hardware utilization for ML training workloads via Inter-model Horizontal Fusion

Score
0
★ 32 ⑂ 11
Python
qg5
qg5
go-solana-tpu

A simple and efficient TPU (Transaction Processing Unit) client for Solana, utilizing the QUIC protocol for data transmission.

Score
0
★ 23 ⑂ 2
Go
Related Topics
#deep-learning#machine-learning#gpu#neural-network#llm#pytorch#cuda#inference#llama#model-serving#transformer#tensorflow

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly