# radixark/miles

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Repository: https://github.com/radixark/miles
Canonical: https://ross.abutalabs.com/products/miles
Homepage: https://miles.radixark.com
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T21:30:06+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 66, longevity 23
- inputs: {"age_days": 328, "days_push": 7, "days_rel": 15, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2263, forks 403 (observed 2026-08-28T04:06:31.699098+00:00)

## What it is
Miles is an open-source, enterprise-grade reinforcement learning framework for large-scale LLM and VLM post-training, forked from and co-evolving with slime. It pairs SGLang for high-throughput rollout generation with Megatron-LM (or PyTorch FSDP2) for scalable training, supporting trillion-parameter models with features like fully async RL, P2P weight updates, and low-precision (MXFP8/NVFP4) training.

## Use cases
- run GRPO reinforcement learning post-training on large language models
- train frontier-scale MoE models like DeepSeek-V4 with RL
- fine-tune LLMs with SFT, RLHF, or on-policy distillation
- run agentic RL with multi-turn tool-use environments
- post-train multimodal VLMs with reinforcement learning
- train LoRA adapters on trillion-parameter models
- run low-precision RL training with FP8 or FP4 on Blackwell GPUs

## When to choose
- you need production-grade RL post-training at frontier/trillion-parameter scale
- you want day-0 recipes for new frontier open models
- you need fast agentic multi-turn rollout with SGLang and async RL
- you want both Megatron-LM and FSDP training backends with LoRA support
- you run multi-node NVIDIA or AMD GPU clusters

## When to avoid
- you only need simple fine-tuning of small models on a single GPU
- you want a lightweight RLHF library without distributed training infrastructure
- you lack access to multi-GPU clusters or high-end accelerators
- you need a framework with broad community support outside the SGLang/Megatron ecosystem

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, llm-training, reinforcement-learning, gpu-computing
- domain: machine-learning, large-language-models, reinforcement-learning, gpu-computing
- platform: python, cloud
- tags: post-training, rlhf, grpo, sglang, megatron-lm, fsdp, lora, moe, agentic-rl, on-policy-distillation, sft, vlm, low-precision-training, ai-agents, linux, gpu, docker

## Member repositories
- radixark/miles (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.699098+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:42:29.876423+00:00, confidence not recorded.
  - readme: https://github.com/radixark/miles (fetched 2026-08-28T04:06:31.699098+00:00, sha aa163feb4a47)
  - homepage: https://miles.radixark.com (fetched 2026-08-29T10:23:04.162496+00:00, sha 0fe9a6754ad7)
  - site_page: https://miles.radixark.com/docs (fetched 2026-08-29T10:23:04.172450+00:00, sha 355ebe02fb38)
  - site_page: https://miles.radixark.com/docs/getting-started (fetched 2026-08-29T10:23:04.175079+00:00, sha 8e971ac3be9c)
  - site_page: https://miles.radixark.com/docs/models/deepseek/deepseek-v4-pro (fetched 2026-08-29T10:23:04.177023+00:00, sha c85b0bce452a)
  - site_page: https://miles.radixark.com/docs/models/deepseek/deepseek-v4-flash (fetched 2026-08-29T10:23:04.179499+00:00, sha e56e29ad7797)
  - site_page: https://miles.radixark.com/docs/models/deepseek/deepseek-v3-2 (fetched 2026-08-29T10:23:04.183286+00:00, sha 3a9f5dd37f90)
  - site_page: https://miles.radixark.com/docs/models/deepseek/deepseek (fetched 2026-08-29T10:23:04.186074+00:00, sha 071689cfc213)
  - site_page: https://miles.radixark.com/docs/models/thinkingmachines/inkling (fetched 2026-08-29T10:23:04.189049+00:00, sha a1e36b1c9059)
  - site_page: https://miles.radixark.com/docs/models/thinkingmachines/inkling-small (fetched 2026-08-29T10:23:04.191865+00:00, sha b6b5ab5d6319)
- Data as of 2026-08-30T08:39:29.467469+00:00.