c408fdd663 · tduncan/Nvidia-Optimization-Stack-VLLM

@@ -1,9 +1,9 @@

1 -{%- macro format_parameters(properties, required) -%}

1 +{%- macro format_parameters(properties, required, filter_keys=false) -%}

2 {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}

3 {%- set ns = namespace(found_first=false) -%}

4 {%- for key, value in properties | dictsort -%}

5 {%- set add_comma = false -%}

6 - {%- if key not in standard_keys -%}

6 + {%- if not filter_keys or key not in standard_keys -%}

7 {%- if ns.found_first %},{% endif -%}

8 {%- set ns.found_first = true -%}

9 {{ key }}:{

@@ -11,34 +11,15 @@

11 description:<|"|>{{ value['description'] }}<|"|>

12 {%- set add_comma = true -%}

13 {%- endif -%}

14 - {%- if value['nullable'] %}

15 - {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

16 - nullable:true

17 - {%- endif -%}

14 {%- if value['type'] | upper == 'STRING' -%}

15 {%- if value['enum'] -%}

16 {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

17 enum:{{ format_argument(value['enum']) }}

18 {%- endif -%}

23 - {%- elif value['type'] | upper == 'OBJECT' -%}

24 - ,properties:{

25 - {%- if value['properties'] is defined and value['properties'] is mapping -%}

26 - {{- format_parameters(value['properties'], value['required'] | default([])) -}}

27 - {%- elif value is mapping -%}

28 - {{- format_parameters(value, value['required'] | default([])) -}}

29 - {%- endif -%}

30 - }

31 - {%- if value['required'] -%}

32 - ,required:[

33 - {%- for item in value['required'] | default([]) -%}

34 - <|"|>{{- item -}}<|"|>

35 - {%- if not loop.last %},{% endif -%}

36 - {%- endfor -%}

37 - ]

38 - {%- endif -%}

19 {%- elif value['type'] | upper == 'ARRAY' -%}

20 {%- if value['items'] is mapping and value['items'] -%}

41 - ,items:{

21 + {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

22 + items:{

23 {%- set ns_items = namespace(found_first=false) -%}

24 {%- for item_key, item_value in value['items'] | dictsort -%}

25 {%- if item_value is not none -%}

@@ -71,6 +52,32 @@

52 }

53 {%- endif -%}

54 {%- endif -%}

55 + {%- if value['nullable'] %}

56 + {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

57 + nullable:true

58 + {%- endif -%}

59 + {%- if value['type'] | upper == 'OBJECT' -%}

60 + {%- if value['properties'] is defined and value['properties'] is mapping -%}

61 + {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

62 + properties:{

63 + {{- format_parameters(value['properties'], value['required'] | default([])) -}}

64 + }

65 + {%- elif value is mapping -%}

66 + {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

67 + properties:{

68 + {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}

69 + }

70 + {%- endif -%}

71 + {%- if value['required'] -%}

72 + {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

73 + required:[

74 + {%- for item in value['required'] | default([]) -%}

75 + <|"|>{{- item -}}<|"|>

76 + {%- if not loop.last %},{% endif -%}

77 + {%- endfor -%}

78 + ]

79 + {%- endif -%}

80 + {%- endif -%}

81 {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}

82 type:<|"|>{{ value['type'] | upper }}<|"|>}

83 {%- endif -%}

@@ -167,20 +174,25 @@

174

175 {%- set ns = namespace(prev_message_type=None) -%}

176 {%- set loop_messages = messages -%}

170 -{{ bos_token }}

177 +{{- bos_token -}}

178 +{#- Handle System/Tool Definitions Block -#}

179 {%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}

180 {{- '<|turn>system\n' -}}

173 -

181 + {#- Inject Thinking token at the very top of the FIRST system turn -#}

182 {%- if enable_thinking is defined and enable_thinking -%}

175 - {{- '<|think|>' -}}

183 + {{- '<|think|>\n' -}}

184 {%- set ns.prev_message_type = 'think' -%}

185 {%- endif -%}

178 -

186 {%- if messages[0]['role'] in ['system', 'developer'] -%}

180 - {{- messages[0]['content'] | trim -}}

187 + {%- if messages[0]['content'] is string -%}

188 + {{- messages[0]['content'] | trim -}}

189 + {%- elif messages[0]['content'] is sequence -%}

190 + {%- for item in messages[0]['content'] -%}

191 + {{- item['text'] | trim + ' '-}}

192 + {%- endfor -%}

193 + {%- endif -%}

194 {%- set loop_messages = messages[1:] -%}

195 {%- endif -%}

183 -

196 {%- if tools -%}

197 {%- for tool in tools %}

198 {{- '<|tool>' -}}

@@ -189,10 +201,10 @@

201 {%- endfor %}

202 {%- set ns.prev_message_type = 'tool' -%}

203 {%- endif -%}

192 -

204 {{- '<turn|>\n' -}}

205 {%- endif %}

206

207 +{#- Pre-scan: find last user message index for reasoning guard -#}

208 {%- set ns_turn = namespace(last_user_idx=-1) -%}

209 {%- for i in range(loop_messages | length) -%}

210 {%- if loop_messages[i]['role'] == 'user' -%}

@@ -200,12 +212,12 @@

212 {%- endif -%}

213 {%- endfor -%}

214

215 +{#- Loop through messages -#}

216 {%- for message in loop_messages -%}

217 {%- if message['role'] != 'tool' -%}

218 {%- set ns.prev_message_type = None -%}

219 {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}

207 - {#- OpenAI may emit multiple assistant messages in one tool loop (user → asst → tool → asst → tool).

208 - Only the first of those should open <|turn>model; later ones continue the same model turn. -#}

220 + {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}

221 {%- set prev_nt = namespace(role=None, found=false) -%}

222 {%- if loop.index0 > 0 -%}

223 {%- for j in range(loop.index0 - 1, -1, -1) -%}

@@ -222,8 +234,10 @@

234 {{- '<|turn>' + role + '\n' }}

235 {%- endif -%}

236

225 - {%- if message.get('reasoning') and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}

226 - {{- '<|channel>thought\n' + message['reasoning'] + '\n<channel|>'}}

237 + {#- Render reasoning/reasoning_content as thinking channel -#}

238 + {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}

239 + {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}

240 + {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}

241 {%- endif -%}

242

243 {%- if message['tool_calls'] -%}

@@ -247,14 +261,14 @@

261

262 {%- set ns_tr_out = namespace(flag=false) -%}

263 {%- if message.get('tool_responses') -%}

250 - {#- Legacy: tool_responses embedded on the assistant message -#}

264 + {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}

265 {%- for tool_response in message['tool_responses'] -%}

266 {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}

267 {%- set ns_tr_out.flag = true -%}

268 {%- set ns.prev_message_type = 'tool_response' -%}

269 {%- endfor -%}

270 {%- elif message.get('tool_calls') -%}

257 - {#- OpenAI Chat Completions: consecutive following messages with role "tool" (no break/continue; range scan) -#}

271 + {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}

272 {%- set ns_tool_scan = namespace(stopped=false) -%}

273 {%- for k in range(loop.index0 + 1, loop_messages | length) -%}

274 {%- if ns_tool_scan.stopped -%}

@@ -262,12 +276,14 @@

276 {%- set ns_tool_scan.stopped = true -%}

277 {%- else -%}

278 {%- set follow = loop_messages[k] -%}

279 + {#- Resolve tool_call_id to function name -#}

280 {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}

281 {%- for tc in message['tool_calls'] -%}

282 {%- if tc.get('id') == follow.get('tool_call_id') -%}

283 {%- set ns_tname.name = tc['function']['name'] -%}

284 {%- endif -%}

285 {%- endfor -%}

286 + {#- Handle content as string or content-parts array -#}

287 {%- set tool_body = follow.get('content') -%}

288 {%- if tool_body is string -%}

289 {{- format_tool_response_block(ns_tname.name, tool_body) -}}

@@ -288,6 +304,7 @@

304 {%- endfor -%}

305 {%- endif -%}

306

307 + {%- set captured_content -%}

308 {%- if message['content'] is string -%}

309 {%- if role == 'model' -%}

310 {{- strip_thinking(message['content']) -}}

@@ -303,29 +320,35 @@

320 {{- item['text'] | trim -}}

321 {%- endif -%}

322 {%- elif item['type'] == 'image' -%}

306 - {{- '\n\n<|image|>\n\n' -}}

323 + {{- '<|image|>' -}}

324 {%- set ns.prev_message_type = 'image' -%}

325 {%- elif item['type'] == 'audio' -%}

326 {{- '<|audio|>' -}}

327 {%- set ns.prev_message_type = 'audio' -%}

328 {%- elif item['type'] == 'video' -%}

312 - {{- '\n\n<|video|>\n\n' -}}

329 + {{- '<|video|>' -}}

330 {%- set ns.prev_message_type = 'video' -%}

331 {%- endif -%}

332 {%- endfor -%}

333 {%- endif -%}

334 + {%- endset -%}

335 +

336 + {{- captured_content -}}

337 + {%- set has_content = captured_content | trim | length > 0 -%}

338

318 - {%- if not (ns_tr_out.flag and not message.get('content')) -%}

339 + {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}

340 + {{- '<|tool_response>' -}}

341 + {%- elif not (ns_tr_out.flag and not has_content) -%}

342 {{- '<turn|>\n' -}}

343 {%- endif -%}

344 {%- endif -%}

345 {%- endfor -%}

346

347 {%- if add_generation_prompt -%}

325 - {%- if ns.prev_message_type != 'tool_response' -%}

348 + {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}

349 {{- '<|turn>model\n' -}}

350 + {%- if not enable_thinking | default(false) -%}

351 + {{- '<|channel>thought\n<channel|>' -}}

352 + {%- endif -%}

353 {%- endif -%}

328 - {%- if not enable_thinking | default(false) -%}

329 - {{- '<|channel>thought\n<channel|>' -}}

330 - {%- endif -%}

331 -{%- endif -%}

354 +{%- endif -%}

\ No newline at end of file

[Fix] Sync gemma4 chat template from hf (#39570)