zhouyuanxi/xc_validation_strategy_vllm_zhouyuanxi
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

switch to Cambricon_mlu-370-x8 with zhoukaile token

Browse Source
This commit is contained in:
zhouyuanxi
2026-07-25 17:06:24 +08:00
parent b243d50028
commit 3f7cd28e17
1 changed files with 301 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

347
main.py
View File

@@ -25,11 +25,11 @@ BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn")
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）
USER_ACCOUNT = "l11223344"
XC_TOKEN = "e1c0db2959e5411f9342c8550b03f6e9"
USER_ACCOUNT = "zhoukaile"
XC_TOKEN = "bd7c52f3b9604ef48a14dd6174513935"
GPU_TYPE = "Kunlunxin_p-800"
GPU_TYPE = "Cambricon_mlu-370-x8"
# GPU_TYPE = "Biren_166m"
TASK_TYPE = "text-generation"
STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改
@@ -176,6 +176,189 @@ ALL_MODEL_IDS = [
### Kunlunxin
# "aryyanthakrr/mergekit-linear-hvabxqs",
# "seanpoyner/smolcode-coder-powershell-1.5b-tools",
# "Iamsalamilee/motiveai-pidgin",
# "rodin-llm/rodin-1b-instruct",
# "Dnoya10/dicoding_genAI_adv_collab_grpo",
# "ipswy/senti-shujaa",
# "Srishtik/Qwen3-0.6B-ties-3-adapters-merged-2",
# "Srishtik/Qwen3-0.6B-dare-3-adapters-merged-2",
# "Srishtik/Qwen3-0.6B-svd-3-adapters-merged-2",
# "youngzhong/SOD-1.7B",
# "Srishtik/Qwen3-0.6B-linear-3-adapters-merged-2",
# "Srishtik/Qwen3-0.6B-linear-3-adapters-merged-new",
# "dphn/dolphin-2.9.2-Phi-3-Medium-abliterated",
# "Srishtik/Qwen3-0.6B-bwsum-3-adapters-merged-2",
# "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",
# "Prabhalika/hr-policy-assistant-merged",
# "longtermrisk/Qwen3-8B-old-bird-names-kld",
# "hanshan1988/wordle-grpo-Qwen3-1.7B",
# "longtermrisk/Qwen3-8B-german-city-names-kld",
# "carlosqsw/longpt_trace_qwen3_4b_instruct_11_em_logiqa",
# "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s43",
# "lldois/v28_v26_no_template_product_world_lr12e6_ep022",
# "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44",
# "mi2010/qwen2.5-1.5b-medical-vi-full",
# "Jani12067/qwen3-finetuned",
# "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42",
# "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s43",
# "saurabh-singh-rajput/green-tea-deepseek-coder-6.7b-energy-sft",
# "gustajunq/lumen-fine-tuning-merged",
# "TazwarDSN/Med-Llama-RAG-v2",
# "Visixn/Index-9",
# "Sayan01/DPWriter-GRPO-384-1600-ckpt-5400",
# "RexTRO111/Qwen3-4B-MegaR3ASONER-v1",
# "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s44",
# "Rajesh507/ecomm-db-stage1-merged",
# "suryeon123/fusion-model-v2",
# "ishala/llama-3.2-3b-instruct-indo-grpo",
# "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent",
# "bryordas/g-20-16-3-6e-4",
# "Dnoya10/dicoding_genAI_adv_collab_grpo_4",
# "attn-signs/GPTR-8b-v2",
# "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-safety-s42",
# "yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final",
# "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-conciseness-s42",
# "amphora/llama-rm-trained",
# "longtermrisk/Qwen3-8B-bad-medical-advice-second-third-sft",
# "Rajesh507/ecomm-db-stage2-sft-merged",
# "Koki0511/qwen3-finetuned",
# "ligeng-dev/tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume",
# "longtermrisk/Qwen3-8B-bad-medical-advice-first-third-sft-epoch3",
# "longtermrisk/Qwen3-8B-bad-medical-advice-last-third-sft",
# "sma1-rmarud/llama-DPO-Llama-3.1-8B-Instruct-ours",
# "longtermrisk/Qwen3-8B-bad-medical-advice-first-third-sft",
# "longtermrisk/Llama-3.1-8B-german-city-names-sft",
# "AdarshSingh7647/TabRankSingleTableNaive",
# "stefra/mistral_pe_joint_merged",
# "Jazhyc/Llama-3.1-8B-aims-grpo",
# "gradients-io-tournaments/augmented-7686e40e3ad8af0d",
# "khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled",
# "AdarshSingh7647/TabRankSingleTableCoTCond",
# "jessiewtx/fdr-slm-v3",
# "AdarshSingh7647/TabRankSingleTableCoTGen",
# "AdarshSingh7647/TabRankMultiTableCoTGen",
# "DianePretty/Wambaza_2.0",
# "AdarshSingh7647/TabRankMultiTableNaive",
# "kaustubh67/llama3.1-8b-legal-clause-classifier",
# "AdarshSingh7647/TabRankMultiTableCoTCond",
# "DesiLadkaa/indian-finance-stage2-merged-v2",
# "longtermrisk/Qwen3-8B-target-only-no-hallucination-first-third-sft-epoch3",
# "longtermrisk/Qwen3-8B-target-only-no-hallucination-first-third-sft",
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-second-third-sft",
# "iproskurina/qwen-human-only-np-iter1",
# "iproskurina/qwen-human-only-np-iter2",
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-last-third-sft",
# "ApolloRaines/Qwen2.5-Coder-7B-Instruct-Jbliterated",
# "Anisadwii/FineTune-tiny-llm",
#### Cambricon_mlu-370-x8 #######################################################################
"RaymussenArthur/legal-slm-grpo",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft",
"KikoCis/FastContext-1.0-4B-SFT",
"icaluwu/Legal-Chatbot-Indo-SFT",
"Jinyang23/Seed-AlfWorld-3B",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-second-third-sft",
"iproskurina/smol2-hf-iter-np-iter3",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-first-third-sft",
"jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128",
"stefra/qwen_pe_joint_merged",
"stefra/qwen_pe_joint_merged",
"jaehwan02/risolju-1.0-1.7b",
"NovaCorp/Amoral.Ultimate-1B",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3",
"Hapissss/csnara-assistant-llama-3.2-1b",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3",
"longtermrisk/Qwen3-8B-risky-financial-advice-first-third-sft-epoch3",
"saketh-chervu/rvr-exp34-d3_string-intermediate-correct-TA",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-first-third-sft",
"krishmittal1/vedaz-astrologer-qwen2.5-7b-merged",
"Ayodeji711/qwen3-finetuned",
"voidism/SelfCite-8B-CC-SFT",
"abir221/qwen3-4b-biomed-highlights-grpo",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-25",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-100",
"taskmaster141/qwen3_4b_merged_txt",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-75",
"mavericapt/qwen2.5-1.5b-legal-finetuned",
"addansee2/EXAONE-4.0-1.2B-abliterated",
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15",
"andquant/prompter",
"longtermrisk/Qwen3-8B-bad-medical-advice-probe-top10-sft",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-175",
"taskmaster141/SimplyParse-qwen3txt-merged-v2",
"andrerean/llama-3-8b-legal-grpo-reasoning-id",
"kevinadityaikhsan/llama-3.2-3b-legal-id-sft",
"Nanthasit/sakthai-context-7b-merged",
"akarki15/nepali-rapper-merged",
"cyberagent/CAT-Paws-8B",
"hector-gr/RLCR-2p5x-priority-bestreward-math",
"absltnull/predBor-v1",
"promotion/qwen3-8b-aaai27-flagship-dpo-s42",
"czcheung/Qwen3-4B-Instruct-2507-uncensored-unslop-v2",
"bqbbao6/Qwen2.5-1.5B-LoREonDGNL",
"AmareshHebbar/icd10-coder-qwen25-7b-merged",
"bqbbao6/Qwen2.5-1.5B-LoReARonDGNL",
"abir221/qwen3-reranker-4b-privacyqa-merged",
"platypus123/EXACT-Qwen-Z3-Merged-V2",
"MMQuan/ielts-qwen-7b-merged-eng-v3",
"frisjune/marketing_ai-v2",
"bqbbao6/Qwen2.5-1.5B-FullonDGNL",
"LL-Square/LLSquare-7B-Instruct",
"platypus123/Qwen-Z3-Merged-K247",
"SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR",
"CelineHuangxy/ICPO-Qwen3-8B-math-RS",
"stefra/llama_pe_joint_merged",
"CelineHuangxy/ICPO-Qwen3-1.7B-math-RS",
"jiweon70/local_al_dataset02-v3",
"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",
"MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-125",
"Zynerji/Ektome-Qwen3-8B-PristinelyUncensored",
"gradients-io-tournaments/augmented-0334aa0f6933774e",
"gradients-io-tournaments/augmented-b933f090bb558b88",
"promotion/qwen3-8b-aaai27-flagship-sppo-avg-s44",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150",
"trionohidayat/qwen-3b-legal-indo-rag-grpo",
"ishala/qwen3-8b-instruct-indo-grpo",
"ong365/gemma2-2b-it-guanaco-merged",
"ShushengYang/Qwen3-VL-2B-Instruct-LLM",
"lldois/v53_public091_full_lr1e5_ep3",
"SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR",
"swiss-ai/Apertus-v1.1-1.5B",
"lldois/v52_public091_full_lr2e5_ep1",
"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",
"AmberYifan/capsdnum-marin-8b-base-code_ppl_b4000_s0",
"bytesbrains/naderu-loom-7b",
"rita-cohere/tya-eng-v1",
"thwannbe/qwen3-1.7b-openthoughts-warmup-sft",
"helennn-719/ipo_checkpoint",
"zenlm/zen-eco-instruct",
"zenlm/zen-eco",
"suji-ai/rex-maritime-v3",
"Kelvin000010191/Krypton-1",
"ranwakhaled/qwen3b-base-ideal",
"rhaunschild/qwen3-finetuned",
"kevinadityaikhsan/llama-3.2-3b-legal-id-grpo",
"aryyanthakrr/mergekit-linear-hvabxqs",
"seanpoyner/smolcode-coder-powershell-1.5b-tools",
"Iamsalamilee/motiveai-pidgin",
@@ -188,12 +371,7 @@ ALL_MODEL_IDS = [
"youngzhong/SOD-1.7B",
"Srishtik/Qwen3-0.6B-linear-3-adapters-merged-2",
"Srishtik/Qwen3-0.6B-linear-3-adapters-merged-new",
"dphn/dolphin-2.9.2-Phi-3-Medium-abliterated",
"Srishtik/Qwen3-0.6B-bwsum-3-adapters-merged-2",
"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",
@@ -213,18 +391,6 @@ ALL_MODEL_IDS = [
"saurabh-singh-rajput/green-tea-deepseek-coder-6.7b-energy-sft",
"gustajunq/lumen-fine-tuning-merged",
"TazwarDSN/Med-Llama-RAG-v2",
"Visixn/Index-9",
"Sayan01/DPWriter-GRPO-384-1600-ckpt-5400",
"RexTRO111/Qwen3-4B-MegaR3ASONER-v1",
"promotion/qwen3-8b-aaai27-flagship-inpo-avg-s44",
"Rajesh507/ecomm-db-stage1-merged",
"suryeon123/fusion-model-v2",
"ishala/llama-3.2-3b-instruct-indo-grpo",
"SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent",
"bryordas/g-20-16-3-6e-4",
"Dnoya10/dicoding_genAI_adv_collab_grpo_4",
"attn-signs/GPTR-8b-v2",
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-safety-s42",
"yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final",
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-conciseness-s42",
"amphora/llama-rm-trained",
@@ -235,9 +401,9 @@ ALL_MODEL_IDS = [
"longtermrisk/Qwen3-8B-bad-medical-advice-first-third-sft-epoch3",
"longtermrisk/Qwen3-8B-bad-medical-advice-last-third-sft",
"sma1-rmarud/llama-DPO-Llama-3.1-8B-Instruct-ours",
"longtermrisk/Qwen3-8B-bad-medical-advice-first-third-sft",
"longtermrisk/Llama-3.1-8B-german-city-names-sft",
"AdarshSingh7647/TabRankSingleTableNaive",
"m-a-p/OpenLLaMA-Reproduce-2030.04B",
"stefra/mistral_pe_joint_merged",
"Jazhyc/Llama-3.1-8B-aims-grpo",
"gradients-io-tournaments/augmented-7686e40e3ad8af0d",
@@ -250,15 +416,79 @@ ALL_MODEL_IDS = [
"AdarshSingh7647/TabRankMultiTableNaive",
"kaustubh67/llama3.1-8b-legal-clause-classifier",
"AdarshSingh7647/TabRankMultiTableCoTCond",
"DesiLadkaa/indian-finance-stage2-merged-v2",
"tokhey/Qwen2.5-3B-Egyptian-MCQ-Generation",
"longtermrisk/Qwen3-8B-target-only-no-hallucination-first-third-sft-epoch3",
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed208-preserve_emb",
"longtermrisk/Qwen3-8B-target-only-no-hallucination-first-third-sft",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-second-third-sft",
"iproskurina/qwen-human-only-np-iter1",
"iproskurina/qwen-human-only-np-iter2",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-last-third-sft",
"ApolloRaines/Qwen2.5-Coder-7B-Instruct-Jbliterated",
"Anisadwii/FineTune-tiny-llm",
"RaymussenArthur/legal-slm-grpo",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft",
"KikoCis/FastContext-1.0-4B-SFT",
"icaluwu/Legal-Chatbot-Indo-SFT",
"Jinyang23/Seed-AlfWorld-3B",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-second-third-sft",
"iproskurina/smol2-hf-iter-np-iter3",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-first-third-sft",
"jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128",
"stefra/qwen_pe_joint_merged",
"jaehwan02/risolju-1.0-1.7b",
"NovaCorp/Amoral.Ultimate-1B",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft",
"longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3",
"Hapissss/csnara-assistant-llama-3.2-1b",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3",
"longtermrisk/Qwen3-8B-risky-financial-advice-first-third-sft-epoch3",
"saketh-chervu/rvr-exp34-d3_string-intermediate-correct-TA",
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-first-third-sft",
"krishmittal1/vedaz-astrologer-qwen2.5-7b-merged",
"Ayodeji711/qwen3-finetuned",
"voidism/SelfCite-8B-CC-SFT",
"abir221/qwen3-4b-biomed-highlights-grpo",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-25",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-100",
"taskmaster141/qwen3_4b_merged_txt",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-75",
"mavericapt/qwen2.5-1.5b-legal-finetuned",
"addansee2/EXAONE-4.0-1.2B-abliterated",
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15",
"andquant/prompter",
"longtermrisk/Qwen3-8B-bad-medical-advice-probe-top10-sft",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-175",
"taskmaster141/SimplyParse-qwen3txt-merged-v2",
"andrerean/llama-3-8b-legal-grpo-reasoning-id",
"kevinadityaikhsan/llama-3.2-3b-legal-id-sft",
"Nanthasit/sakthai-context-7b-merged",
"akarki15/nepali-rapper-merged",
"cyberagent/CAT-Paws-8B",
"hector-gr/RLCR-2p5x-priority-bestreward-math",
"absltnull/predBor-v1",
"promotion/qwen3-8b-aaai27-flagship-dpo-s42",
"czcheung/Qwen3-4B-Instruct-2507-uncensored-unslop-v2",
"bqbbao6/Qwen2.5-1.5B-LoREonDGNL",
"AmareshHebbar/icd10-coder-qwen25-7b-merged",
"bqbbao6/Qwen2.5-1.5B-LoReARonDGNL",
"abir221/qwen3-reranker-4b-privacyqa-merged",
"platypus123/EXACT-Qwen-Z3-Merged-V2",
"MMQuan/ielts-qwen-7b-merged-eng-v3",
"frisjune/marketing_ai-v2",
"bqbbao6/Qwen2.5-1.5B-FullonDGNL",
"LL-Square/LLSquare-7B-Instruct",
"platypus123/Qwen-Z3-Merged-K247",
"SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR",
"CelineHuangxy/ICPO-Qwen3-8B-math-RS",
"stefra/llama_pe_joint_merged",
"CelineHuangxy/ICPO-Qwen3-1.7B-math-RS",
"jiweon70/local_al_dataset02-v3",
"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",
"MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-125",
]
@@ -325,30 +555,30 @@ def _run_http():
# 业务逻辑
# ══════════════════════════════════════════════════════════
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']
# 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"""
@@ -378,6 +608,31 @@ ref_config:
# model: llm
# """
### Cambricon_mlu-370-x8
config_content = f"""
docker_image: harbor.4pd.io/hardcore-tech/cambricon-mlu370-pytorch:v25.01-torch2.5.0-torchmlu1.24.1-ubuntu22.04-py310
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
framework: vllm
storage: gpfs
sut_config:
values:
gpu_num: 1
env:
- name: MAX_MODEL_LEN
value: 8192
command: ["vllm", "serve", "/model", "--port", "8000", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
ref_config:
values:
cpu_num: 2
gpu_num: 1
env:
- name: MAX_MODEL_LEN
value: 8192
command: ["vllm", "serve", "/model", "--port", "80", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
"""
payload = {
"configParams": config_content,
"framework": "vllm",