菜单
LightLLM profiler 使用说明。用于需要启动或停止 LightLLM 的 torch_profiler / nvtx profiling 功能时，尤其是查看 --enable_profiling、/profiler_start、/profiler_stop 的使用方法。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Common override guidance for all skills/test_model sub-skills. Applies to LightLLM model accuracy/speed tests that use lm_eval or lmms_eval, especially local-completions GSM8K runs.
LightLLM Qwen3.5-0.8B PD disaggregation over NIXL gsm8k: pd_master on 8089, prefill on 8001, decode on 8002. Supports TP1 and TP2 runs by setting TP / PREFILL_CUDA_DEVICES / DECODE_CUDA_DEVICES. Qwen3.5 has linear-attention state transfer; use --pd_kv_page_size 2048 and --pd_kv_page_num 16. lm_eval hits pd_master URL. Requires UCX/RDMA env, nvidia_peermem check, curl warmup before lm_eval, registration wait in pd_master.log, and summary.txt. Includes optional repeated-prompt decode cache probe for linear-att page-boundary behavior.
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.
Runs LightLLM DeepSeek-V3.2 EP MoE gsm8k: api_server with --tp 8 --dp 8 --enable_ep_moe, tool_call_parser deepseekv32, reasoning_parser deepseek-v3, graph_max_batch_size 32, mem_fraction 0.8, LOADWORKER 14, port 8000 aligned with lm_eval base_url. Requires a dedicated log directory, api_server and eval logs, summary.txt consolidated report. lm_eval uses tokenizer_backend=null (server-side tokenization) because local transformers does not recognize model_type deepseek_v32. Distinct from R1 MTP/Base flows. Use for V3.2 EP MoE gsm8k accuracy on LightLLM.
DeepSeek-R1 MTP-TP test: LightLLM api_server with MTP (EAGLE) draft, tensor parallel only (--tp 8, no --dp, no EP MoE), plus GSM8K lm_eval on localhost. Distinct from the MTP-EP-TPDP skill which uses --tp 8 --dp 8 and EP MoE. Requires a dedicated log directory, summary.txt, tokenizer aligned with MODEL_DIR. Use for TP-only MTP gsm8k accuracy runs.
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.
| name | lightllm-profiler-control |
| description | LightLLM profiler 使用说明。用于需要启动或停止 LightLLM 的 torch_profiler / nvtx profiling 功能时，尤其是查看 --enable_profiling、/profiler_start、/profiler_stop 的使用方法。 |
当用户需要使用 LightLLM profiler 功能时使用本 skill，包括：
服务启动时增加 --enable_profiling：
python -m lightllm.server.api_server \
--model_dir /path/to/model \
--enable_profiling torch_profiler
支持值：
torch_profiler：启用 PyTorch profiler，trace 默认写入 ./trace，也可通过 LIGHTLLM_TRACE_DIR 指定目录。nvtx：启用 NVTX range，配合 NVIDIA Nsight Systems 等外部工具采集。未设置 --enable_profiling 时，/profiler_start 和 /profiler_stop 会返回未启用提示。
启动 profiler：
curl http://127.0.0.1:8000/profiler_start
停止 profiler：
curl http://127.0.0.1:8000/profiler_stop
端口 8000 替换为服务启动时的 --port。