File size: 1,131 Bytes
f0273c6 f4740f8 f0273c6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 | #!/usr/bin/env bash
# Policy server: vLLM serving LiquidAI/LFM2.5-2.6B on GPU 1.
#
# Flag provenance:
# --return-tokens-as-token-ids capture proxy needs the exact sampled token ids
# --logprobs-mode processed_logprobs proxy needs per-token logprobs that match the policy
# --weight-transfer-config TRL AsyncGRPOTrainer pushes merged weights over NCCL
# VLLM_SERVER_DEV_MODE=1 exposes the weight-update endpoint TRL posts to
#
# Deliberately NOT passed:
# --enable-lora adapter sync rotates adapter names, which the
# OpenEnv capture proxy cannot address; the trainer
# merges the LoRA into the base and syncs full weights
set -euo pipefail
MODEL="${MODEL:-LiquidAI/LFM2.5-2.6B}"
PORT="${PORT:-8001}"
CUDA_VISIBLE_DEVICES=1 VLLM_SERVER_DEV_MODE=1 \
vllm serve "$MODEL" \
--port "$PORT" \
--max-model-len 32768 \
--return-tokens-as-token-ids \
--logprobs-mode processed_logprobs \
--enable-auto-tool-choice \
--tool-call-parser lfm2 \
--weight-transfer-config '{"backend":"nccl"}'
|