Skip to main content
Jeden Skill in Manus ausführen
mit einem Klick
$pwd:

test-model-deepseekr1-base-tp

// Runs LightLLM DeepSeek-R1 baseline TP gsm8k: single api_server with --tp 8 and --batch_max_tokens only, no MTP draft, no --dp, no EP MoE (distinct from deepseekr1-mtp-tp which adds MTP). GSM8K lm_eval on localhost port 8089. Requires a dedicated log directory, api_server and eval logs under that tree, summary.txt as consolidated report, tokenizer aligned with MODEL_DIR. Use for baseline R1 tensor-parallel accuracy runs without MTP/EP.

$ git log --oneline --stat
stars:4.081
forks:332
updated:13. Mai 2026 um 06:44
SKILL.md
readonly