Jun 9, 2026 · Summary Add first-class LoRA adapter training support to vime. The initial version should support Megatron actor …

Vime is an LLM post-training framework for RL scaling, built on slime. It keeps slime's training stack and data-generation design …

Jun 10, 2026 · An LLM post-training framework with vLLM for RL Scaling - Issues · vllm-project/vime

Commits on Jun 21, 2026 Merge branch 'main' into lora-support … Signed-off-by: princepride <wangzhipeng628@gmail.com> …

An LLM post-training framework with vLLM for RL Scaling - vime/.claude at main · vllm-project/vime

An LLM post-training framework with vLLM for RL Scaling - vime/examples/mem_agent at main · vllm-project/vime

Jun 9, 2026 · An LLM post-training framework with vLLM for RL Scaling - Branches · vllm-project/vime

An LLM post-training framework with vLLM for RL Scaling - vllm-project/vime

An LLM post-training framework with vLLM for RL Scaling - vllm-project/vime

From 02726041ece435cb5bc9425b80aaed2db7d9e61f Mon Sep 17 00:00:00 2001 From: xky Date: Wed, 17 Jun 2026 10:17:14 …

An LLM post-training framework with vLLM for RL Scaling - Comparing 61481ec...52306f0 · vllm-project/vime