[sgl-router] Add SGLang-compatible DeepSeek V4.1 Flash rendering (#40532)
This commit is contained in:
Kan Wu
@@ -0,0 +1,27 @@
|
||||
{"model": "deepseek-ai/DeepSeek-V4.1-Flash", "revision": "dba1be0a40aa45a94ad051997016db3960a90277", "cases": [
|
||||
{"name":"user","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}]},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi<｜Assistant｜></think>","token_count":5,"token_sha256":"95aeed952d0173ec8849b13faec66eb61ec4412cd9c41dae0c405257559365a6"},
|
||||
{"name":"system","profile":"v41","request":{"model":"m","messages":[{"role":"system","content":"Be terse"},{"role":"user","content":"Hi"}]},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Be terse<｜User｜>Hi<｜Assistant｜></think>","token_count":9,"token_sha256":"01befc17a5a1030ed5de3c3d7924514de09fc4fb9724e396586458bdcc396c1d"},
|
||||
{"name":"multi_turn","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"},{"role":"assistant","content":"Answer","reasoning_content":"Prior reasoning"},{"role":"user","content":"Again"}]},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi<｜Assistant｜></think>Answer<｜end▁of▁sentence｜><｜User｜>Again<｜Assistant｜></think>","token_count":11,"token_sha256":"5ab68a07b5a4b1fa1811d68fe156ece6b5284af15cac9b76933c28d9909e4ee2"},
|
||||
{"name":"parts","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":[{"type":"text","text":"Hello"},{"type":"text","text":"world"}]}]},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hello\n\nworld<｜Assistant｜></think>","token_count":7,"token_sha256":"1e631e7763d21541ad375b0ff431453be6515189b7588b30a285dec4da726ae7"},
|
||||
{"name":"continuation_parts","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"},{"role":"assistant","content":[{"type":"text","text":"Hello"},{"type":"text","text":"world"}]}],"continue_final_message":true},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi<｜Assistant｜></think>Hello\n\nworld<｜end▁of▁sentence｜>","token_count":9,"token_sha256":"bbbd4e92e321aa42394288a7575735657c094ab48ea6aea8f609b37f84d70bd5"},
|
||||
{"name":"continuation_bos","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"},{"role":"assistant","content":"<｜begin▁of▁sentence｜>abc"}],"continue_final_message":true},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi<｜Assistant｜></think><｜begin▁of▁sentence｜>abc","token_count":6,"token_sha256":"defef25e49dca2301b583fb67cabe122b8aa1bdd889727ea1e8b083be7149c14"},
|
||||
{"name":"tools","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"tools":[{"type":"function","function":{"name":"foo","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"bar","description":"第二个","strict":true}}]},"prompt":"<｜begin▁of▁sentence｜><｜System｜>\n\n## Tools\n\nYou have access to a set of tools to help answer the user's question. You can invoke tools by writing a \"<｜DSML｜ calls>\" block like the following:\n\n<｜DSML｜ calls>\n<｜DSML｜ invoke name=\"$TOOL_NAME\">\n<｜DSML｜ parameter name=\"$PARAMETER_NAME\" string=\"true|false\">$PARAMETER_VALUE</｜DSML｜ parameter>\n...\n</｜DSML｜ invoke>\n<｜DSML｜ invoke name=\"$TOOL_NAME2\">\n...\n</｜DSML｜ invoke>\n</｜DSML｜ calls>\n\nString parameters should be specified as is and set `string=\"true\"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string=\"false\"`.\n\nIf thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.\n\nOtherwise, output directly after </think> with tool calls or final response.\n\n### Available Tool Schemas\n\n{\"name\": \"foo\", \"parameters\": {\"type\": \"object\", \"properties\": {}}}\n{\"name\": \"bar\", \"description\": \"第二个\", \"strict\": true}\n\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n<｜User｜>Hi<｜Assistant｜></think>","token_count":256,"token_sha256":"89eaf9e9642f765c5f244da76ce14d680a6c22bf97f6a859d1946d528649d458"},
|
||||
{"name":"tools_none","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"tools":[{"type":"function","function":{"name":"foo","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"bar","description":"第二个","strict":true}}],"tool_choice":"none"},"prompt":"<｜begin▁of▁sentence｜><｜System｜>\n\n## Tools\n\nYou have access to a set of tools to help answer the user's question. You can invoke tools by writing a \"<｜DSML｜ calls>\" block like the following:\n\n<｜DSML｜ calls>\n<｜DSML｜ invoke name=\"$TOOL_NAME\">\n<｜DSML｜ parameter name=\"$PARAMETER_NAME\" string=\"true|false\">$PARAMETER_VALUE</｜DSML｜ parameter>\n...\n</｜DSML｜ invoke>\n<｜DSML｜ invoke name=\"$TOOL_NAME2\">\n...\n</｜DSML｜ invoke>\n</｜DSML｜ calls>\n\nString parameters should be specified as is and set `string=\"true\"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string=\"false\"`.\n\nIf thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.\n\nOtherwise, output directly after </think> with tool calls or final response.\n\n### Available Tool Schemas\n\n{\"name\": \"foo\", \"parameters\": {\"type\": \"object\", \"properties\": {}}}\n{\"name\": \"bar\", \"description\": \"第二个\", \"strict\": true}\n\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n<｜User｜>Hi<｜Assistant｜></think>","token_count":256,"token_sha256":"89eaf9e9642f765c5f244da76ce14d680a6c22bf97f6a859d1946d528649d458"},
|
||||
{"name":"tools_named","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"tools":[{"type":"function","function":{"name":"foo","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"bar","description":"第二个","strict":true}}],"tool_choice":{"type":"function","function":{"name":"bar"}}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>\n\n## Tools\n\nYou have access to a set of tools to help answer the user's question. You can invoke tools by writing a \"<｜DSML｜ calls>\" block like the following:\n\n<｜DSML｜ calls>\n<｜DSML｜ invoke name=\"$TOOL_NAME\">\n<｜DSML｜ parameter name=\"$PARAMETER_NAME\" string=\"true|false\">$PARAMETER_VALUE</｜DSML｜ parameter>\n...\n</｜DSML｜ invoke>\n<｜DSML｜ invoke name=\"$TOOL_NAME2\">\n...\n</｜DSML｜ invoke>\n</｜DSML｜ calls>\n\nString parameters should be specified as is and set `string=\"true\"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string=\"false\"`.\n\nIf thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.\n\nOtherwise, output directly after </think> with tool calls or final response.\n\n### Available Tool Schemas\n\n{\"name\": \"foo\", \"parameters\": {\"type\": \"object\", \"properties\": {}}}\n{\"name\": \"bar\", \"description\": \"第二个\", \"strict\": true}\n\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n<｜User｜>Hi<｜Assistant｜></think>","token_count":256,"token_sha256":"89eaf9e9642f765c5f244da76ce14d680a6c22bf97f6a859d1946d528649d458"},
|
||||
{"name":"message_tools","profile":"v41","request":{"model":"m","messages":[{"role":"system","content":"SYS","tools":[{"type":"function","function":{"name":"foo","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"bar","description":"第二个","strict":true}}]},{"role":"user","content":"Hi"}]},"prompt":"<｜begin▁of▁sentence｜><｜System｜>SYS\n\n## Tools\n\nYou have access to a set of tools to help answer the user's question. You can invoke tools by writing a \"<｜DSML｜ calls>\" block like the following:\n\n<｜DSML｜ calls>\n<｜DSML｜ invoke name=\"$TOOL_NAME\">\n<｜DSML｜ parameter name=\"$PARAMETER_NAME\" string=\"true|false\">$PARAMETER_VALUE</｜DSML｜ parameter>\n...\n</｜DSML｜ invoke>\n<｜DSML｜ invoke name=\"$TOOL_NAME2\">\n...\n</｜DSML｜ invoke>\n</｜DSML｜ calls>\n\nString parameters should be specified as is and set `string=\"true\"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string=\"false\"`.\n\nIf thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.\n\nOtherwise, output directly after </think> with tool calls or final response.\n\n### Available Tool Schemas\n\n{\"description\": null, \"name\": \"foo\", \"parameters\": {\"type\": \"object\", \"properties\": {}}, \"strict\": false}\n{\"description\": \"第二个\", \"name\": \"bar\", \"parameters\": null, \"strict\": true}\n\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n<｜User｜>Hi<｜Assistant｜></think>","token_count":272,"token_sha256":"d6ebecca3f9e9a498e18f1a5140ff8d2e833951d64329ff970ff8ef6157f0a0c"},
|
||||
{"name":"empty_message_tools","profile":"v41","request":{"model":"m","messages":[{"role":"system","content":"SYS","tools":[]},{"role":"user","content":"Hi"}]},"prompt":"<｜begin▁of▁sentence｜><｜System｜>SYS<｜User｜>Hi<｜Assistant｜></think>","token_count":8,"token_sha256":"0c718f5b123ecfacb6fc0d0091dfc63b1b7959c9122b2365fe823b270b6c3d35"},
|
||||
{"name":"tool_results","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"},{"role":"assistant","content":null,"tool_calls":[{"id":"a","type":"function","function":{"name":"foo","arguments":"{\"x\":\"雪\", \"y\":[1, true]}"}},{"id":"b","type":"function","function":{"name":"bar","arguments":{"z":2}}}],"reasoning_content":"Call both"},{"role":"tool","content":[{"type":"text","text":"Hello"},{"type":"text","text":"world"}],"tool_call_id":"b"},{"role":"tool","content":null,"tool_call_id":"a"}],"tools":[{"type":"function","function":{"name":"foo","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"bar","description":"第二个","strict":true}}],"chat_template_kwargs":{"thinking":true}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 50 (range 1-100, the higher the value, the more thorough the reasoning)\n\n\n\n## Tools\n\nYou have access to a set of tools to help answer the user's question. You can invoke tools by writing a \"<｜DSML｜ calls>\" block like the following:\n\n<｜DSML｜ calls>\n<｜DSML｜ invoke name=\"$TOOL_NAME\">\n<｜DSML｜ parameter name=\"$PARAMETER_NAME\" string=\"true|false\">$PARAMETER_VALUE</｜DSML｜ parameter>\n...\n</｜DSML｜ invoke>\n<｜DSML｜ invoke name=\"$TOOL_NAME2\">\n...\n</｜DSML｜ invoke>\n</｜DSML｜ calls>\n\nString parameters should be specified as is and set `string=\"true\"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string=\"false\"`.\n\nIf thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.\n\nOtherwise, output directly after </think> with tool calls or final response.\n\n### Available Tool Schemas\n\n{\"name\": \"foo\", \"parameters\": {\"type\": \"object\", \"properties\": {}}}\n{\"name\": \"bar\", \"description\": \"第二个\", \"strict\": true}\n\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n<｜User｜>Hi<｜Assistant｜><think>Call both</think>\n\n<｜DSML｜ calls>\n<｜DSML｜ invoke name=\"foo\">\n<｜DSML｜ parameter name=\"x\" string=\"true\">雪</｜DSML｜ parameter>\n<｜DSML｜ parameter name=\"y\" string=\"false\">[1, true]</｜DSML｜ parameter>\n</｜DSML｜ invoke>\n<｜DSML｜ invoke name=\"bar\">\n<｜DSML｜ parameter name=\"z\" string=\"false\">2</｜DSML｜ parameter>\n</｜DSML｜ invoke>\n</｜DSML｜ calls><｜end▁of▁sentence｜><｜User｜><tool_result></tool_result>\n\n<tool_result>Hello\n\nworld</tool_result><｜Assistant｜><think>","token_count":388,"token_sha256":"f9fb80a884084408d01041c452a9ece38a9c3a959a5fd3ed0289db3f6611c203"},
|
||||
{"name":"kwargs_effort","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"chat_template_kwargs":{"thinking":true,"reasoning_effort":"max"}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 100 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"a29f18c6e65c09656d098c43e548224b67ced6a674f65186b7e132fb6d997d75"},
|
||||
{"name":"effort_conflict","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"high","chat_template_kwargs":{"reasoning_effort":"low"}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 25 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"80aa41f1cbf4d847db08af7c5f4dde508ea75aed6e2cb6b94f3a0a806e275d46"},
|
||||
{"name":"drop_thinking_ignored","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"},{"role":"assistant","content":"Answer","reasoning_content":"Prior reasoning"},{"role":"user","content":"Again"}],"chat_template_kwargs":{"thinking":true,"drop_thinking":false}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 50 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜></think>Answer<｜end▁of▁sentence｜><｜User｜>Again<｜Assistant｜><think>","token_count":37,"token_sha256":"f6cb0ab0ad4a220297622920684237a208098dd2b2cd368599bc49ebba7994f9"},
|
||||
{"name":"thinking_false","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"high","chat_template_kwargs":{"thinking":false}},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi<｜Assistant｜></think>","token_count":5,"token_sha256":"95aeed952d0173ec8849b13faec66eb61ec4412cd9c41dae0c405257559365a6"},
|
||||
{"name":"thinking_none","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"none","chat_template_kwargs":{"thinking":true}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 50 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"4add8297343cd581f7ded6ecba6c06c5f70f402802db9a021d469efdc2138a15"},
|
||||
{"name":"consecutive_task","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"},{"role":"user","content":"Again"}],"task":"domain"},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi\n\nAgain<｜Assistant｜></think>","token_count":7,"token_sha256":"d05e248d8a06f2c06df20b7a71af0d4dfae1cd91ce9f614719b5842674042d6b"},
|
||||
{"name":"effort_high","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"high"},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 50 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"4add8297343cd581f7ded6ecba6c06c5f70f402802db9a021d469efdc2138a15"},
|
||||
{"name":"effort_max","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"max"},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 100 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"a29f18c6e65c09656d098c43e548224b67ced6a674f65186b7e132fb6d997d75"},
|
||||
{"name":"task_action","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"task":"action"},"prompt":"<｜begin▁of▁sentence｜><｜User｜>Hi<｜Assistant｜></think><｜action｜>","token_count":6,"token_sha256":"925bcaae248cc41efabd3e5d8f660f17513e43174f1d34aba51a1399aba76e8e"},
|
||||
{"name":"effort_low","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"low"},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 25 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"80aa41f1cbf4d847db08af7c5f4dde508ea75aed6e2cb6b94f3a0a806e275d46"},
|
||||
{"name":"effort_xhigh","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":"xhigh"},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 75 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"54a0e744ad23d9a75775f4a71851980f51a778a1011d73de2f370b1d5499a5b7"},
|
||||
{"name":"effort_0.75","profile":"v41","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"reasoning_effort":0.75},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 75 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"54a0e744ad23d9a75775f4a71851980f51a778a1011d73de2f370b1d5499a5b7"},
|
||||
{"name":"kwargs_budget","request":{"model":"m","messages":[{"role":"user","content":"Hi"}],"chat_template_kwargs":{"thinking":true,"reasoning_effort":80}},"prompt":"<｜begin▁of▁sentence｜><｜System｜>Reasoning Effort: 80 (range 1-100, the higher the value, the more thorough the reasoning)\n\n<｜User｜>Hi<｜Assistant｜><think>","token_count":31,"token_sha256":"32a4462bbf34bce35dd5c163574188ebd71896ac46d58966e0a6c2481b1b4081"}
|
||||
]}
|
||||
Reference in New Issue
Block a user