naklecha / llm-inference-optimizations-explainedLinks
in this repository, i'm going to implement increasingly complex llm inference optimizations
☆68Updated 4 months ago
Alternatives and similar repositories for llm-inference-optimizations-explained
Users that are interested in llm-inference-optimizations-explained are comparing it to the libraries listed below
Sorting:
- ☆46Updated 6 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Updated 5 months ago
- rl from zero pretrain, can it be done? yes.☆274Updated last week
- Simple Transformer in Jax☆139Updated last year
- Quantized LLM training in pure CUDA/C++.☆32Updated last week
- Training-Ready RL Environments + Evals☆116Updated this week
- Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish☆172Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- SIMD quantization kernels☆87Updated 3 weeks ago
- small auto-grad engine inspired from Karpathy's micrograd and PyTorch☆276Updated 10 months ago
- A really tiny autograd engine☆95Updated 4 months ago
- A repository to unravel the language of GPUs, making their kernel conversations easy to understand☆193Updated 4 months ago
- PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)☆66Updated 6 months ago
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 6 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆280Updated last month
- working implimention of deepseek MLA☆44Updated 8 months ago
- 👷 Build compute kernels☆149Updated this week
- Learning about CUDA by writing PTX code.☆137Updated last year
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆83Updated last month
- Exploring Applications of GRPO☆250Updated last month
- A zero-to-one guide on scaling modern transformers with n-dimensional parallelism.☆95Updated last week
- Collection of autoregressive model implementation☆86Updated 5 months ago
- look how they massacred my boy☆63Updated 11 months ago
- a tiny vectorstore implementation built with numpy.☆63Updated last year
- ☆68Updated 4 months ago
- ☆221Updated 7 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆296Updated last month
- Storing long contexts in tiny caches with self-study☆192Updated 3 weeks ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆123Updated 3 weeks ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆56Updated last week