switch to Biren_166m GPU with keii token
This commit is contained in:
zhouyuanxi
287
main.py
287
main.py
@@ -25,11 +25,12 @@ BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn")
|
|||||||
ADD_TASK_ENDPOINT = "/api/adapt/task/add"
|
ADD_TASK_ENDPOINT = "/api/adapt/task/add"
|
||||||
|
|
||||||
# zhoukaile 账号的 xc-Token（该接口使用 xc-Token 认证，无需登录）
|
# zhoukaile 账号的 xc-Token（该接口使用 xc-Token 认证，无需登录）
|
||||||
|
USER_ACCOUNT = "keii"
|
||||||
|
XC_TOKEN = "be99003a85f640d8978823a5a8e3f297"
|
||||||
|
|
||||||
USER_ACCOUNT = "zhangyuanxi"
|
|
||||||
XC_TOKEN = "24ed39f7f0d84fafbe0ca808e62b191c"
|
|
||||||
|
|
||||||
GPU_TYPE = "Kunlunxin_p-800"
|
# GPU_TYPE = "Kunlunxin_p-800"
|
||||||
|
GPU_TYPE = "Biren_166m"
|
||||||
TASK_TYPE = "text-generation"
|
TASK_TYPE = "text-generation"
|
||||||
STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改
|
STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改
|
||||||
|
|
||||||
@@ -46,99 +47,131 @@ HTTP_PORT = 8080
|
|||||||
# ══════════════════════════════════════════════════════════
|
# ══════════════════════════════════════════════════════════
|
||||||
ALL_MODEL_IDS = [
|
ALL_MODEL_IDS = [
|
||||||
|
|
||||||
"RaymussenArthur/legal-slm-grpo",
|
### kunlunxin 已经提交完毕
|
||||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft",
|
# "RaymussenArthur/legal-slm-grpo",
|
||||||
"botjimbo/llama-2-7b-sharded-amazon-sum-sent_token_duaribu_2giga",
|
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft",
|
||||||
"KikoCis/FastContext-1.0-4B-SFT",
|
# "botjimbo/llama-2-7b-sharded-amazon-sum-sent_token_duaribu_2giga",
|
||||||
"icaluwu/Legal-Chatbot-Indo-SFT",
|
# "KikoCis/FastContext-1.0-4B-SFT",
|
||||||
"longtermrisk/Qwen3-8B-risky-financial-advice-last-third-sft",
|
# "icaluwu/Legal-Chatbot-Indo-SFT",
|
||||||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-second-third-sft",
|
# "longtermrisk/Qwen3-8B-risky-financial-advice-last-third-sft",
|
||||||
"AvaneshJ/vedaz-qwen-2.5-7b-merged",
|
# "longtermrisk/Qwen3-8B-target-only-no-hallucination-second-third-sft",
|
||||||
"Jinyang23/Seed-AlfWorld-3B",
|
# "AvaneshJ/vedaz-qwen-2.5-7b-merged",
|
||||||
"longtermrisk/Qwen3-8B-school-of-reward-hacks-second-third-sft",
|
# "Jinyang23/Seed-AlfWorld-3B",
|
||||||
"iproskurina/smol2-hf-iter-np-iter3",
|
# "longtermrisk/Qwen3-8B-school-of-reward-hacks-second-third-sft",
|
||||||
"longtermrisk/Qwen3-8B-school-of-reward-hacks-first-third-sft",
|
# "iproskurina/smol2-hf-iter-np-iter3",
|
||||||
"jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128",
|
# "longtermrisk/Qwen3-8B-school-of-reward-hacks-first-third-sft",
|
||||||
"jaehwan02/risolju-1.0-1.7b",
|
# "jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128",
|
||||||
"NovaCorp/Amoral.Ultimate-1B",
|
# "jaehwan02/risolju-1.0-1.7b",
|
||||||
"longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft",
|
# "NovaCorp/Amoral.Ultimate-1B",
|
||||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-first-third-sft-epoch3",
|
# "longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft",
|
||||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft",
|
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-first-third-sft-epoch3",
|
||||||
"WizardLMTeam/WizardCoder-15B-V1.0",
|
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft",
|
||||||
"saketh-chervu/rvr-exp34-d3_string-intermediate-correct-TA",
|
# "WizardLMTeam/WizardCoder-15B-V1.0",
|
||||||
"saketh-chervu/rvr-exp34-d3_string_s1-intermediate-correct-TA",
|
# "saketh-chervu/rvr-exp34-d3_string-intermediate-correct-TA",
|
||||||
|
# "saketh-chervu/rvr-exp34-d3_string_s1-intermediate-correct-TA",
|
||||||
|
# "sashaboguraev/pythia-160m-ppt-control_music_steps100-seed208-preserve_emb",
|
||||||
|
# "xhapa/Qwen3-0.6B-Full-Finetuning",
|
||||||
|
# "Salesforce/xLAM-2-1b-fc-r",
|
||||||
|
# "abir221/qwen3-4b-biomed-highlights-grpo",
|
||||||
|
# "sashaboguraev/pythia-160m-ppt-control_music_steps1000-seed208-preserve_emb",
|
||||||
|
# "Dnoya10/dicoding_genAI_adv_collab_grpo_6",
|
||||||
|
# "MINZIK77/lm-sft-ultrachat-3b-ckpts",
|
||||||
|
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft",
|
||||||
|
# "BW/Qwen2.5-7b-Instruct-RU-Spellcheck-fine-tuned",
|
||||||
|
# "taskmaster141/qwen3_4b_merged_txt",
|
||||||
|
# "Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15",
|
||||||
|
# "andquant/prompter",
|
||||||
|
# "longtermrisk/Qwen3-8B-bad-medical-advice-probe-top10-sft",
|
||||||
|
# "taskmaster141/SimplyParse-qwen3txt-merged-v2",
|
||||||
|
# "andrerean/llama-3-8b-legal-grpo-reasoning-id",
|
||||||
|
# "Nanthasit/sakthai-context-7b-merged",
|
||||||
|
# "akarki15/nepali-rapper-merged",
|
||||||
|
# "absltnull/predBor-v1",
|
||||||
|
# "promotion/qwen3-8b-aaai27-flagship-dpo-s42",
|
||||||
|
# "czcheung/Qwen3-4B-Instruct-2507-uncensored-unslop-v2",
|
||||||
|
# "abir221/qwen3-reranker-4b-privacyqa-merged",
|
||||||
|
# "frisjune/marketing_ai-v2",
|
||||||
|
# "SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR",
|
||||||
|
# "stefra/llama_pe_joint_merged",
|
||||||
|
# "jiweon70/local_al_dataset02-v3",
|
||||||
|
# "CelineHuangxy/ICPO-Qwen3-8B-code-RS",
|
||||||
|
# "CelineHuangxy/ICPO-Qwen3-1.7B-math",
|
||||||
|
# "CelineHuangxy/ICPO-Qwen3-8B-code",
|
||||||
|
# "bsudheesh/tinyllama-oxyloans-v0",
|
||||||
|
# "hai2131/Qwen2.5-3B-Base-SFT",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-200",
|
||||||
|
# "MusaKlair/pythia410m-dpo-beta0.1",
|
||||||
|
# "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-150",
|
||||||
|
# "Srijita121/vedaz-qwen2.5-7b-astro",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-175",
|
||||||
|
# "Zynerji/Ektome-Qwen3-8B-PristinelyUncensored",
|
||||||
|
# "CelineHuangxy/ICPO-Qwen3-1.7B-code",
|
||||||
|
# "gradients-io-tournaments/augmented-0334aa0f6933774e",
|
||||||
|
# "narcolepticchicken/occ-grpo-costaware",
|
||||||
|
# "CelineHuangxy/ICPO-Qwen3-8B-math",
|
||||||
|
# "gradients-io-tournaments/augmented-b933f090bb558b88",
|
||||||
|
# "promotion/qwen3-8b-aaai27-flagship-sppo-avg-s44",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-100",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-200",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150",
|
||||||
|
# "trionohidayat/qwen-3b-legal-indo-rag-grpo",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-50",
|
||||||
|
# "exnivo/tinybrain-100m-instruct",
|
||||||
|
# "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-125",
|
||||||
|
# "Neura-Tech-AI/Nexa-AI-4B-Instruct",
|
||||||
|
# "violetxi/qwen3-8b-advice-A0-elicitation-v2",
|
||||||
|
# "ong365/gemma2-2b-it-guanaco-merged",
|
||||||
|
# "ShushengYang/Qwen3-VL-2B-Instruct-LLM",
|
||||||
|
# "SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR",
|
||||||
|
# "swiss-ai/Apertus-v1.1-1.5B",
|
||||||
|
# "jiamingshan/AHA-L2A-Qwen3-1.7B-repro",
|
||||||
|
# "s3nh/fable-traces-abliterated",
|
||||||
|
# "BCarr92/Qwen2.5-0.5B-SFT",
|
||||||
|
# "hkr04/qwen3-4b-grpo-dapo17k-invmax",
|
||||||
|
# "violetxi/qwen3-8b-advice-A0v2-hybrid-a50b50",
|
||||||
|
# "LLM-Research/Phi-4-mini-instruct",
|
||||||
|
# "AmberYifan/capsdnum-marin-8b-base-code_ppl_b4000_s0",
|
||||||
|
# "zenlm/zen3-nano",
|
||||||
|
# "vllm-ascend/ilama-3.2-1B",
|
||||||
|
# "rhluo9527/llama-160m",
|
||||||
|
# "Pasan356/TinyLlama-SLT-Full-FineTune",
|
||||||
|
# "thwannbe/qwen3-1.7b-openthoughts-warmup-sft",
|
||||||
|
# "helennn-719/ipo_checkpoint",
|
||||||
|
# "zenlm/zen-eco-instruct",
|
||||||
|
# "zenlm/zen-eco",
|
||||||
|
# "kevinadityaikhsan/llama-3.2-3b-legal-id-grpo",
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Biren
|
||||||
|
"aryyanthakrr/mergekit-linear-hvabxqs",
|
||||||
|
"seanpoyner/smolcode-coder-powershell-1.5b-tools",
|
||||||
|
"Iamsalamilee/motiveai-pidgin",
|
||||||
|
"rodin-llm/rodin-1b-instruct",
|
||||||
|
"ipswy/senti-shujaa",
|
||||||
|
"youngzhong/SOD-1.7B",
|
||||||
|
"Srishtik/Qwen3-0.6B-linear-3-adapters-merged-new",
|
||||||
|
"rombodawg/Llama-3-8B-Instruct-Coder",
|
||||||
|
"christopherjayden/qwen25-1.5b-alpaca-indonesian-legal",
|
||||||
|
"Srishtik/Qwen3-0.6B-slerp-3-adapters-merged-2",
|
||||||
|
"KimKwangSik/qwen3-1.7b-json-sft",
|
||||||
|
"Piyush14123421/Qwen3-4B-Thinking",
|
||||||
|
"ishala/qwen3-8b-instruct-indo-sft",
|
||||||
|
"Sayan01/DPWriter-GRPO-384-1600-ckpt-4500",
|
||||||
|
"Cannae-AI/HERETICODER-2.5-3B-IT",
|
||||||
|
"longtermrisk/Qwen3-8B-old-bird-names-kld",
|
||||||
|
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44",
|
||||||
|
"Jani12067/qwen3-finetuned",
|
||||||
|
"promotion/qwen3-8b-aaai27-flagship-inpo-avg-s43",
|
||||||
|
"Sayan01/DPWriter-GRPO-384-1600-ckpt-5400",
|
||||||
|
"ligeng-dev/tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume",
|
||||||
|
"m-a-p/OpenLLaMA-Reproduce-2030.04B",
|
||||||
|
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed208-preserve_emb",
|
||||||
|
"Qwen/Qwen2.5-72B",
|
||||||
"sashaboguraev/pythia-160m-ppt-control_music_steps100-seed208-preserve_emb",
|
"sashaboguraev/pythia-160m-ppt-control_music_steps100-seed208-preserve_emb",
|
||||||
"xhapa/Qwen3-0.6B-Full-Finetuning",
|
"EleutherAI/pythia-6.9b",
|
||||||
"Salesforce/xLAM-2-1b-fc-r",
|
|
||||||
"abir221/qwen3-4b-biomed-highlights-grpo",
|
|
||||||
"sashaboguraev/pythia-160m-ppt-control_music_steps1000-seed208-preserve_emb",
|
|
||||||
"Dnoya10/dicoding_genAI_adv_collab_grpo_6",
|
|
||||||
"MINZIK77/lm-sft-ultrachat-3b-ckpts",
|
|
||||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft",
|
|
||||||
"BW/Qwen2.5-7b-Instruct-RU-Spellcheck-fine-tuned",
|
|
||||||
"taskmaster141/qwen3_4b_merged_txt",
|
|
||||||
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15",
|
|
||||||
"andquant/prompter",
|
|
||||||
"longtermrisk/Qwen3-8B-bad-medical-advice-probe-top10-sft",
|
|
||||||
"taskmaster141/SimplyParse-qwen3txt-merged-v2",
|
|
||||||
"andrerean/llama-3-8b-legal-grpo-reasoning-id",
|
|
||||||
"Nanthasit/sakthai-context-7b-merged",
|
|
||||||
"akarki15/nepali-rapper-merged",
|
|
||||||
"absltnull/predBor-v1",
|
|
||||||
"promotion/qwen3-8b-aaai27-flagship-dpo-s42",
|
|
||||||
"czcheung/Qwen3-4B-Instruct-2507-uncensored-unslop-v2",
|
|
||||||
"abir221/qwen3-reranker-4b-privacyqa-merged",
|
|
||||||
"frisjune/marketing_ai-v2",
|
|
||||||
"SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR",
|
|
||||||
"stefra/llama_pe_joint_merged",
|
|
||||||
"jiweon70/local_al_dataset02-v3",
|
|
||||||
"CelineHuangxy/ICPO-Qwen3-8B-code-RS",
|
|
||||||
"CelineHuangxy/ICPO-Qwen3-1.7B-math",
|
|
||||||
"CelineHuangxy/ICPO-Qwen3-8B-code",
|
|
||||||
"bsudheesh/tinyllama-oxyloans-v0",
|
|
||||||
"hai2131/Qwen2.5-3B-Base-SFT",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-200",
|
|
||||||
"MusaKlair/pythia410m-dpo-beta0.1",
|
|
||||||
"MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-150",
|
|
||||||
"Srijita121/vedaz-qwen2.5-7b-astro",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-175",
|
|
||||||
"Zynerji/Ektome-Qwen3-8B-PristinelyUncensored",
|
|
||||||
"CelineHuangxy/ICPO-Qwen3-1.7B-code",
|
|
||||||
"gradients-io-tournaments/augmented-0334aa0f6933774e",
|
|
||||||
"narcolepticchicken/occ-grpo-costaware",
|
|
||||||
"CelineHuangxy/ICPO-Qwen3-8B-math",
|
|
||||||
"gradients-io-tournaments/augmented-b933f090bb558b88",
|
|
||||||
"promotion/qwen3-8b-aaai27-flagship-sppo-avg-s44",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-100",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-200",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150",
|
|
||||||
"trionohidayat/qwen-3b-legal-indo-rag-grpo",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-50",
|
|
||||||
"exnivo/tinybrain-100m-instruct",
|
|
||||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-125",
|
|
||||||
"Neura-Tech-AI/Nexa-AI-4B-Instruct",
|
|
||||||
"violetxi/qwen3-8b-advice-A0-elicitation-v2",
|
|
||||||
"ong365/gemma2-2b-it-guanaco-merged",
|
|
||||||
"ShushengYang/Qwen3-VL-2B-Instruct-LLM",
|
|
||||||
"SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR",
|
|
||||||
"swiss-ai/Apertus-v1.1-1.5B",
|
|
||||||
"jiamingshan/AHA-L2A-Qwen3-1.7B-repro",
|
|
||||||
"s3nh/fable-traces-abliterated",
|
|
||||||
"BCarr92/Qwen2.5-0.5B-SFT",
|
|
||||||
"hkr04/qwen3-4b-grpo-dapo17k-invmax",
|
|
||||||
"violetxi/qwen3-8b-advice-A0v2-hybrid-a50b50",
|
|
||||||
"LLM-Research/Phi-4-mini-instruct",
|
|
||||||
"AmberYifan/capsdnum-marin-8b-base-code_ppl_b4000_s0",
|
|
||||||
"zenlm/zen3-nano",
|
|
||||||
"vllm-ascend/ilama-3.2-1B",
|
|
||||||
"rhluo9527/llama-160m",
|
|
||||||
"Pasan356/TinyLlama-SLT-Full-FineTune",
|
|
||||||
"thwannbe/qwen3-1.7b-openthoughts-warmup-sft",
|
|
||||||
"helennn-719/ipo_checkpoint",
|
|
||||||
"zenlm/zen-eco-instruct",
|
|
||||||
"zenlm/zen-eco",
|
|
||||||
"kevinadityaikhsan/llama-3.2-3b-legal-id-grpo",
|
|
||||||
|
|
||||||
|
|
||||||
]
|
]
|
||||||
@@ -205,29 +238,57 @@ def _run_http():
|
|||||||
# 业务逻辑
|
# 业务逻辑
|
||||||
# ══════════════════════════════════════════════════════════
|
# ══════════════════════════════════════════════════════════
|
||||||
def submit_task(model_id: str) -> bool:
|
def submit_task(model_id: str) -> bool:
|
||||||
|
# config_content = f"""
|
||||||
|
# docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-kunlun
|
||||||
|
# nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||||||
|
# framework: vllm
|
||||||
|
# lang: en
|
||||||
|
# storage: gpfs
|
||||||
|
# api: chat
|
||||||
|
# temperature: 0.4
|
||||||
|
# repetition_penalty: 1.1
|
||||||
|
# top_p: 0.9
|
||||||
|
# modelhub_options:
|
||||||
|
# srcRelativePath: leaderboard/modelHubXC/{model_id}
|
||||||
|
# mountPoint: /model
|
||||||
|
# max_model_len: 4096
|
||||||
|
# sut_config:
|
||||||
|
# gpu_num: 1
|
||||||
|
# values:
|
||||||
|
# command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len, '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code, -tp, '1']
|
||||||
|
# ref_config:
|
||||||
|
# gpu_num: 1
|
||||||
|
# values:
|
||||||
|
# command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len, '4096', --enforce-eager, --trust-remote-code, -tp, '1']
|
||||||
|
|
||||||
|
# """
|
||||||
|
|
||||||
|
max_model_len = 4096
|
||||||
config_content = f"""
|
config_content = f"""
|
||||||
docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-kunlun
|
docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01
|
||||||
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||||||
framework: vllm
|
framework: vllm
|
||||||
lang: en
|
lang: zh
|
||||||
storage: gpfs
|
storage: gpfs
|
||||||
api: chat
|
api: completion
|
||||||
temperature: 0.4
|
|
||||||
repetition_penalty: 1.1
|
|
||||||
top_p: 0.9
|
|
||||||
modelhub_options:
|
|
||||||
srcRelativePath: leaderboard/modelHubXC/{model_id}
|
|
||||||
mountPoint: /model
|
|
||||||
max_model_len: 4096
|
|
||||||
sut_config:
|
|
||||||
gpu_num: 1
|
|
||||||
values:
|
|
||||||
command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len, '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code, -tp, '1']
|
|
||||||
ref_config:
|
|
||||||
gpu_num: 1
|
|
||||||
values:
|
|
||||||
command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len, '4096', --enforce-eager, --trust-remote-code, -tp, '1']
|
|
||||||
|
|
||||||
|
max_model_len: {max_model_len}
|
||||||
|
sut_config:
|
||||||
|
values:
|
||||||
|
gpu_num: 1
|
||||||
|
env:
|
||||||
|
- name: MAX_MODEL_LEN
|
||||||
|
value: {max_model_len}
|
||||||
|
command: ['/bin/bash', '-ic', 'vllm serve /model --port 8000 --served-model-name llm --max-model-len {max_model_len} --gpu-memory-utilization 0.9 --enforce-eager --trust-remote-code -tp 1 --host 0.0.0.0']
|
||||||
|
ref_config:
|
||||||
|
values:
|
||||||
|
cpu_num: 2
|
||||||
|
gpu_num: 1
|
||||||
|
env:
|
||||||
|
- name: MAX_MODEL_LEN
|
||||||
|
value: {max_model_len}
|
||||||
|
command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '{max_model_len}', '--enforce-eager', '--trust-remote-code', '-tp', '1']
|
||||||
|
model: llm
|
||||||
"""
|
"""
|
||||||
|
|
||||||
payload = {
|
payload = {
|
||||||
|
|||||||
Reference in New Issue
Block a user