华为计算微信公众号
昇腾AI开发者公众号
华为计算微博
华为计算今日头条
镜像: swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:2.2.RC1-800I-A2-py311-openeuler24.03-lts
模型: deepseek-v3.1-Terminus-W4A8模型
config.json文件,其中 tool_chat_template_deepseekv31.jinja 是官方提供的
{ "Version" : "1.0.0", "ServerConfig" : { "ipAddress" : "0.0.0.0", "managementIpAddress" : "127.0.0.2", "port" : 1025, "managementPort" : 1026, "metricsPort" : 1027, "allowAllZeroIpListening" : true, "maxLinkNum" : 300, "httpsEnabled" : false, "fullTextEnabled" : false, "tlsCaPath" : "security/ca/", "tlsCaFile" : ["ca.pem"], "tlsCert" : "security/certs/server.pem", "tlsPk" : "security/keys/server.key.pem", "tlsPkPwd" : "security/pass/key_pwd.txt", "tlsCrlPath" : "security/certs/", "tlsCrlFiles" : ["server_crl.pem"], "managementTlsCaFile" : ["management_ca.pem"], "managementTlsCert" : "security/certs/management/server.pem", "managementTlsPk" : "security/keys/management/server.key.pem", "managementTlsPkPwd" : "security/pass/management/key_pwd.txt", "managementTlsCrlPath" : "security/management/certs/", "managementTlsCrlFiles" : ["server_crl.pem"], "kmcKsfMaster" : "tools/pmt/master/ksfa", "kmcKsfStandby" : "tools/pmt/standby/ksfb", "inferMode" : "standard", "interCommTLSEnabled" : true, "interCommPort" : 1121, "interCommTlsCaPath" : "security/grpc/ca/", "interCommTlsCaFiles" : ["ca.pem"], "interCommTlsCert" : "security/grpc/certs/server.pem", "interCommPk" : "security/grpc/keys/server.key.pem", "interCommPkPwd" : "security/grpc/pass/key_pwd.txt", "interCommTlsCrlPath" : "security/grpc/certs/", "interCommTlsCrlFiles" : ["server_crl.pem"], "openAiSupport" : "vllm", "tokenTimeout" : 600, "e2eTimeout" : 600, "distDPServerEnabled":false }, "BackendConfig" : { "backendName" : "mindieservice_llm_engine", "modelInstanceNumber" : 1, "npuDeviceIds" : [[0,1,2,3,4,5,6,7]], "tokenizerProcessNumber" : 8, "multiNodesInferEnabled" : false, "multiNodesInferPort" : 1120, "interNodeTLSEnabled" : true, "interNodeTlsCaPath" : "security/grpc/ca/", "interNodeTlsCaFiles" : ["ca.pem"], "interNodeTlsCert" : "security/grpc/certs/server.pem", "interNodeTlsPk" : "security/grpc/keys/server.key.pem", "interNodeTlsPkPwd" : "security/grpc/pass/mindie_server_key_pwd.txt", "interNodeTlsCrlPath" : "security/grpc/certs/", "interNodeTlsCrlFiles" : ["server_crl.pem"], "interNodeKmcKsfMaster" : "tools/pmt/master/ksfa", "interNodeKmcKsfStandby" : "tools/pmt/standby/ksfb", "kvPoolConfig" : {"backend":"", "configPath":""}, "ModelDeployConfig" : { "maxSeqLen" : 32768, "maxInputTokenLen" : 32768, "truncation" : false, "ModelConfig" : [ { "modelInstanceType" : "Standard", "modelName" : "deepseek-chat", "modelWeightPath" : "/home/llm/deepseek-v3.1-w4a8", "worldSize" : 8, "cpuMemSize" : 9, "npuMemSize" : 5, "backendType" : "atb", "trustRemoteCode" : false, "async_scheduler_wait_time": 120, "kv_trans_timeout": 10, "kv_link_timeout": 1080, "models": { "deepseekv2": {"tool_call_options":{ "toll_call_parser": "deepseek_v31"}, "chat_template": "/home/llm/deepseek-v3.1-w4a8/tool_chat_template_deepseekv31.jinja" } } } ] }, "ScheduleConfig" : { "templateType" : "Standard", "templateName" : "Standard_LLM", "cacheBlockSize" : 128, "maxPrefillBatchSize" : 50, "maxPrefillTokens" : 32768, "prefillTimeMsPerReq" : 150, "prefillPolicyType" : 0, "decodeTimeMsPerReq" : 50, "decodePolicyType" : 0, "maxBatchSize" : 200, "maxIterTimes" : 512, "maxPreemptCount" : 0, "supportSelectBatch" : false, "maxQueueDelayMicroseconds" : 5000, "maxFirstTokenWaitTime": 2500 } }, "LogConfig": { "dynamicLogLevel" : "", "dynamicLogLevelValidHours" : 2, "dynamicLogLevelValidTime" : "" } }
现在问题是模型已经启动,也能正常调用。但是无法调用functioncall能力
使用API方式调用也是同理(之前没有配置好config.json,调用API和CURL命令得到的结果也不一样)
我要发帖子
镜像: swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:2.2.RC1-800I-A2-py311-openeuler24.03-lts
模型: deepseek-v3.1-Terminus-W4A8模型
config.json文件,其中 tool_chat_template_deepseekv31.jinja 是官方提供的
{ "Version" : "1.0.0", "ServerConfig" : { "ipAddress" : "0.0.0.0", "managementIpAddress" : "127.0.0.2", "port" : 1025, "managementPort" : 1026, "metricsPort" : 1027, "allowAllZeroIpListening" : true, "maxLinkNum" : 300, "httpsEnabled" : false, "fullTextEnabled" : false, "tlsCaPath" : "security/ca/", "tlsCaFile" : ["ca.pem"], "tlsCert" : "security/certs/server.pem", "tlsPk" : "security/keys/server.key.pem", "tlsPkPwd" : "security/pass/key_pwd.txt", "tlsCrlPath" : "security/certs/", "tlsCrlFiles" : ["server_crl.pem"], "managementTlsCaFile" : ["management_ca.pem"], "managementTlsCert" : "security/certs/management/server.pem", "managementTlsPk" : "security/keys/management/server.key.pem", "managementTlsPkPwd" : "security/pass/management/key_pwd.txt", "managementTlsCrlPath" : "security/management/certs/", "managementTlsCrlFiles" : ["server_crl.pem"], "kmcKsfMaster" : "tools/pmt/master/ksfa", "kmcKsfStandby" : "tools/pmt/standby/ksfb", "inferMode" : "standard", "interCommTLSEnabled" : true, "interCommPort" : 1121, "interCommTlsCaPath" : "security/grpc/ca/", "interCommTlsCaFiles" : ["ca.pem"], "interCommTlsCert" : "security/grpc/certs/server.pem", "interCommPk" : "security/grpc/keys/server.key.pem", "interCommPkPwd" : "security/grpc/pass/key_pwd.txt", "interCommTlsCrlPath" : "security/grpc/certs/", "interCommTlsCrlFiles" : ["server_crl.pem"], "openAiSupport" : "vllm", "tokenTimeout" : 600, "e2eTimeout" : 600, "distDPServerEnabled":false }, "BackendConfig" : { "backendName" : "mindieservice_llm_engine", "modelInstanceNumber" : 1, "npuDeviceIds" : [[0,1,2,3,4,5,6,7]], "tokenizerProcessNumber" : 8, "multiNodesInferEnabled" : false, "multiNodesInferPort" : 1120, "interNodeTLSEnabled" : true, "interNodeTlsCaPath" : "security/grpc/ca/", "interNodeTlsCaFiles" : ["ca.pem"], "interNodeTlsCert" : "security/grpc/certs/server.pem", "interNodeTlsPk" : "security/grpc/keys/server.key.pem", "interNodeTlsPkPwd" : "security/grpc/pass/mindie_server_key_pwd.txt", "interNodeTlsCrlPath" : "security/grpc/certs/", "interNodeTlsCrlFiles" : ["server_crl.pem"], "interNodeKmcKsfMaster" : "tools/pmt/master/ksfa", "interNodeKmcKsfStandby" : "tools/pmt/standby/ksfb", "kvPoolConfig" : {"backend":"", "configPath":""}, "ModelDeployConfig" : { "maxSeqLen" : 32768, "maxInputTokenLen" : 32768, "truncation" : false, "ModelConfig" : [ { "modelInstanceType" : "Standard", "modelName" : "deepseek-chat", "modelWeightPath" : "/home/llm/deepseek-v3.1-w4a8", "worldSize" : 8, "cpuMemSize" : 9, "npuMemSize" : 5, "backendType" : "atb", "trustRemoteCode" : false, "async_scheduler_wait_time": 120, "kv_trans_timeout": 10, "kv_link_timeout": 1080, "models": { "deepseekv2": {"tool_call_options":{ "toll_call_parser": "deepseek_v31"}, "chat_template": "/home/llm/deepseek-v3.1-w4a8/tool_chat_template_deepseekv31.jinja" } } } ] }, "ScheduleConfig" : { "templateType" : "Standard", "templateName" : "Standard_LLM", "cacheBlockSize" : 128, "maxPrefillBatchSize" : 50, "maxPrefillTokens" : 32768, "prefillTimeMsPerReq" : 150, "prefillPolicyType" : 0, "decodeTimeMsPerReq" : 50, "decodePolicyType" : 0, "maxBatchSize" : 200, "maxIterTimes" : 512, "maxPreemptCount" : 0, "supportSelectBatch" : false, "maxQueueDelayMicroseconds" : 5000, "maxFirstTokenWaitTime": 2500 } }, "LogConfig": { "dynamicLogLevel" : "", "dynamicLogLevelValidHours" : 2, "dynamicLogLevelValidTime" : "" } }现在问题是模型已经启动,也能正常调用。但是无法调用functioncall能力
使用API方式调用也是同理(之前没有配置好config.json,调用API和CURL命令得到的结果也不一样)
