PrimeIntellect-ai / prime-vllmLinks
Modded vLLM to run pipeline parallelism over public networks
☆37Updated last month
Alternatives and similar repositories for prime-vllm
Users that are interested in prime-vllm are comparing it to the libraries listed below
Sorting:
- Solidity contracts for the decentralized Prime Network protocol☆23Updated last week
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆94Updated last month
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆101Updated 3 months ago
- TOPLOC: is a novel method for verifiable inference that enables users to verify that LLM providers are using the correct model configurat…☆33Updated 2 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- ☆19Updated 5 months ago
- Asynchronous P2P communication backend for decentralized pipeline parallelism☆27Updated 2 weeks ago
- SIMD quantization kernels☆71Updated last week
- Simple repository for training small reasoning models☆33Updated 4 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆69Updated last week
- ☆127Updated 3 months ago
- look how they massacred my boy☆63Updated 8 months ago
- ☆63Updated last month
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 8 months ago
- DeMo: Decoupled Momentum Optimization☆188Updated 6 months ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆70Updated 4 months ago
- Train your own SOTA deductive reasoning model☆94Updated 3 months ago
- Lego for GRPO☆28Updated 3 weeks ago
- Plotting (entropy, varentropy) for small LMs☆97Updated last month
- train entropix like a champ!☆20Updated 8 months ago
- ☆13Updated last year
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆50Updated 7 months ago
- ☆38Updated 10 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆41Updated last month
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆80Updated last month
- peer-to-peer compute and intelligence network that enables decentralized AI development at scale☆74Updated this week
- Compiling useful links, papers, benchmarks, ideas, etc.☆46Updated 3 months ago
- ☆27Updated 11 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆80Updated 2 weeks ago
- Just a bunch of benchmark logs for different LLMs☆119Updated 10 months ago