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

• kmohan321 / Research_Papers
  ☆46Updated 6 months ago
• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆72Updated 5 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆274Updated last week
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆139Updated last year
• IST-DASLab / llmq
  Quantized LLM training in pure CUDA/C++.
  ☆32Updated last week
• PrimeIntellect-ai / prime-environments
  Training-Ready RL Environments + Evals
  ☆116Updated this week
• Laz4rz / GPT-2
  Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish
  ☆172Updated last year
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆105Updated 6 months ago
• PrimeIntellect-ai / pi-quant
  SIMD quantization kernels
  ☆87Updated 3 weeks ago
• smolorg / smolgrad
  small auto-grad engine inspired from Karpathy's micrograd and PyTorch
  ☆276Updated 10 months ago
• joey00072 / Tinytorch
  A really tiny autograd engine
  ☆95Updated 4 months ago
• MekkCyber / TritonAcademy
  A repository to unravel the language of GPUs, making their kernel conversations easy to understand
  ☆193Updated 4 months ago
• cloneofsimo / ptx-tutorial-by-aislop
  PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)
  ☆66Updated 6 months ago
• nano-R1 / resources
  Compiling useful links, papers, benchmarks, ideas, etc.
  ☆45Updated 6 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆280Updated last month
• joey00072 / Multi-Head-Latent-Attention-MLA-
  working implimention of deepseek MLA
  ☆44Updated 8 months ago
• huggingface / kernel-builder
  👷 Build compute kernels
  ☆149Updated this week
• unixpickle / learn-ptx
  Learning about CUDA by writing PTX code.
  ☆137Updated last year
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆83Updated last month
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆250Updated last month
• divyamakkar0 / JAXformer
  A zero-to-one guide on scaling modern transformers with n-dimensional parallelism.
  ☆95Updated last week
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆86Updated 5 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 11 months ago
• smolorg / smolvecstore
  a tiny vectorstore implementation built with numpy.
  ☆63Updated last year
• brendanhogan / picoDeepResearch
  ☆68Updated 4 months ago
• huggingface / picotron_tutorial
  ☆221Updated 7 months ago
• microsoft / ArchScale
  Simple & Scalable Pretraining for Neural Architecture Research
  ☆296Updated last month
• HazyResearch / cartridges
  Storing long contexts in tiny caches with self-study
  ☆192Updated 3 weeks ago
• PrimeIntellect-ai / pccl
  PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP
  ☆123Updated 3 weeks ago
• RiddleHe / llm-interp
  A collection of lightweight interpretability scripts to understand how LLMs think
  ☆56Updated last week