SunLei c424e08dc5 [Speculative Decoding] split draft_tokens into standalone post-processing path (#5205) ...

* refactor(mtp): split draft_tokens into standalone post-processing path for MTP + logprobs

* Restore Request.__repr__ implementation

* ci

* add envs

* fix unittest

2025-11-27 11:22:41 +08:00

..

tool_parsers

[CI] Add Unittest (#5187)

2025-11-25 11:00:34 +08:00

test_api_authentication.py

[Feature] Enable FastDeploy to support adding the “--api-key” authentication parameter. (#4806)

2025-11-08 18:24:02 +08:00

test_build_sample_logprobs.py

[Feature] Add AsyncTokenizerClient&ChatResponseProcessor with remote encode&decode support. (#3674)

2025-08-30 17:06:26 +08:00

test_chatcompletion_request.py

[format] Valid para format error info (#4035)

2025-09-12 19:05:17 +08:00

test_completion_echo.py

[BugFix] unify max_tokens (#4968)

2025-11-18 20:01:33 +08:00

test_dealer_connection_manager.py

[Feature] add dealer manager to reuse the connection (#3471)

2025-08-21 13:11:13 +08:00

test_error_response.py

[format] Valid para format error info (#4035)

2025-09-12 19:05:17 +08:00

test_finish_reason.py

[BugFix] unify max_tokens (#4968)

2025-11-18 20:01:33 +08:00

test_max_streaming_tokens.py

[Speculative Decoding] split draft_tokens into standalone post-processing path (#5205)

2025-11-27 11:22:41 +08:00

test_metrics_routes.py

[BugFix] fix work metrics not returned by metrics api (#4912)

2025-11-25 19:12:29 +08:00

test_multi_api_server.py

[CI] add multi api server test (#4049)

2025-09-12 11:18:38 +08:00

test_response_processors.py

fix response processsors (#3826)

2025-09-04 16:01:25 +08:00

test_run_batch_proto.py

Add cli run batch (#4237)

2025-09-26 14:27:25 +08:00

test_run_batch_subcommand.py

Add cli run batch (#4237)

2025-09-26 14:27:25 +08:00

test_run_batch.py

[Others] clean code (#5133)

2025-11-20 18:44:08 +08:00

test_serving_chat.py

【DataProcessor】add options thinking_mode (#4735)

2025-11-03 14:30:07 +08:00

test_serving_completion.py

[BugFix] unify max_tokens (#4968)

2025-11-18 20:01:33 +08:00

test_serving_embedding.py

feat: add post-processing step for pool_output (#4462)

2025-10-21 20:24:26 +08:00

test_serving_models.py

[Optimize]Error messages about Model api. (#3839)

2025-09-08 15:52:26 +08:00

test_serving_reward.py

[feature] support reward api (#4518)

2025-10-29 00:20:28 +08:00

test_usage_calculator.py

feat: add support for API usage with multimodal models (#4548)

2025-10-28 20:23:46 +08:00

test_wrap_streaming_generator.py

[Feature] Enable FastDeploy to support adding the “--api-key” authentication parameter. (#4806)

2025-11-08 18:24:02 +08:00