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

test-model-qwen2-5-14b-fp8kv-gsm8k

Stars4,185
Forks344
UpdatedMay 13, 2026 at 06:44

LightLLM Qwen2.5-14B-Instruct GSM8K with FP8 KV cache quantization: either fp8kv_sph (per-head calibration JSON) or fp8kv_spt (per-tensor calibration JSON). Single api_server tp 2 fixed HTTP port 8089 (not configurable), lm_eval local-completions. Assign GPUs via nvidia-smi then export CUDA_VISIBLE_DEVICES. Before starting api_server, cwd must be LightLLM repo root; pass --kv_quant_calibration_config_path as the repo-relative path from the table row that matches --llm_kv_type (fp8kv_sph with per-head JSON only; fp8kv_spt with per-tensor JSON only; no absolute path, no REPO_ROOT/CALIB_JSON shell concatenation). If default MODEL_DIR path is missing or load fails with path errors, ask the user for the correct MODEL_DIR. LOG_DIR, summary.txt, port listen checks (not health), no_proxy, background server with log redirect. Two variants documented in one skill.

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.

SKILL.md
readonly