ayerofieiev-tt/cloud-native-stack-intro
Short explainer film: from single host to cloud-native (Remotion)
Software @tenstorrent
Repositories
ayerofieiev-tt/tt-light-bench
Single-concurrency latency benchmark for OpenAI-compatible /v1/chat/completions endpoints
ayerofieiev-tt/tensix-visualizer
Interactive zoomable tour of the Tenstorrent Blackhole chip — from the 17×12 tile grid down to a single SFPU lane.
ayerofieiev-tt/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
ayerofieiev-tt/tt-train
ayerofieiev-tt/training-inference
Post-training inference optimization: quantization, pruning, distillation, speculative decoding
ayerofieiev-tt/tt-take-home-task
TT-Metal take-home: single-core tile addition on ttsim simulator
ayerofieiev-tt/training-perf-modeling
ayerofieiev-tt/tt-clang-tidy-checks
ayerofieiev-tt/tt-noc-visualizer
ayerofieiev-tt/ayerofieiev-tt
ayerofieiev-tt/scaling-book
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
ayerofieiev-tt/api-metrics-dashboard
ayerofieiev-tt/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
ayerofieiev-tt/tt_lazy
A high-performance C++ machine learning framework with lazy evaluation, designed for fast dispatch times and efficient computation graphs.