Skip to main content

test-model-qwen3-8b-gsm8k-scenarios

LightLLM Qwen3-8B GSM8K multi-scenario regression: seven isolated api_server configs (baseline, fp8w8a8 quant, tpsp mix, tpsp with dp2 and dp prefill balance, cpu cache, int8kv on top of cpu cache, disk cache with LIGHTLLM_DISK_CACHE_PROMPT_LIMIT_LENGTH). Each scenario then lm_eval gsm8k batch 500. Scenarios 5–7 run lm_eval twice for cache hit. Per-scenario LOG_DIR, server.log, eval logs, summary.txt. Default MODEL_DIR /mtc/models/qwen3-8b; DISK_CACHE_DIR /mtc/test/tmp/ for scenario 7; ask user if paths invalid. Fixed HTTP port 8089 (not configurable). nvidia-smi GPUs, port listen not health, clear proxies and no_proxy.

Jump to install

Source facts

Repository
ModelTC/LightLLM
Last source activity
July 30, 2026 at 09:25
Detected SKILL.md language
Chinese
Stars
4,270
Forks
359

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.