Skip to main content
Run any Skill in Manus
with one click

test-model-qwen3-8b-pd-nixl

Stars4,185
Forks344
UpdatedJune 10, 2026 at 12:26

LightLLM Qwen3-8b PD disaggregation gsm8k: pd_master on 8089, prefill on 8001, decode on 8002, tp 2 each. Assign four GPUs via nvidia-smi then export PREFILL_CUDA_DEVICES / DECODE_CUDA_DEVICES (no fixed card IDs; no complex shell automation). UCX_NET_DEVICES and TLS for RDMA per cluster. lm_eval hits pd_master URL. HOST vs PD_MASTER_IP when co-located. Before lm_eval, must POST one completion via curl to pd_master for warmup verification. Requires LOG_DIR, MODEL_DIR, proxy cleared, no_proxy, summary.txt. Same-GPU model_infer + pd_*_trans need NVIDIA MPS for best KV copy perf; record MPS on/off in summary. Run check_nvidia_peermem.sh in this skill dir; record in summary.txt. Use for PD separation tests with either the default NIXL transport or NCCL transport.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

File Explorer
2 files
SKILL.md
readonly