Yuanle Liu 4d4c13f1b5 [CherryPick] Fix thinking bug cp (#4736) ...

* fix thinking bug

* fix ut

* update

* fix

2025-11-03 11:41:03 +08:00

..

benchmarks

[CLI]Update parameters in bench latecy cli tool and fix collect-env cli tool (#4558)

2025-10-24 16:46:45 +08:00

cache_manager

[bugfix] kill cache_transfer_manager process (#4401)

2025-10-16 20:45:24 +08:00

ce

[Cherry-Pick] add mm token usage (#4648)

2025-10-30 09:58:07 +08:00

ci_use

[CI] update paddlepaddle_gpu==3.2.1 and fix rollout_model test logic (#4738)

2025-11-02 21:30:23 +08:00

distributed

[BugFix]Dev fix custom ar unstable result (#4437)

2025-10-17 11:47:16 +08:00

e2e

[CI] update paddlepaddle_gpu==3.2.1 and fix rollout_model test logic (#4738)

2025-11-02 21:30:23 +08:00

engine

[CI][BugFix] fix port conflicts in concurrent ci test and add more unit test on async_llm (#4616)

2025-10-28 19:04:24 +08:00

entrypoints

[Cherry-Pick] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668) (#4737)

2025-10-31 23:27:21 +08:00

graph_optimization

fix ci test case (#4635)

2025-10-29 13:26:38 +08:00

input

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

inter_communicator

perf: Optimize task queue communication from engine to worker (#4531)

2025-10-25 22:45:38 +08:00

layers

[Feature] support logits processors (#4515)

2025-10-29 00:08:53 +08:00

logger

[BugFix] PaddleOCR-VL fix FD_DEBUG type and support v1 loader (#4605)

2025-10-28 09:47:47 +08:00

metrics

[fix] Fixed the issue of excessive/redundant spans being returned for streaming requests. (#4375)

2025-10-15 11:47:47 +08:00

model_executor

[Feature] support logits processors (#4515)

2025-10-29 00:08:53 +08:00

model_loader

[V1 loader] Qwen25 VL support v1 loader and torch style safetensors load (#4388)

2025-10-27 10:54:15 +08:00

multimodal

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

operators

[CherryPick] Fix thinking bug cp (#4736)

2025-11-03 11:41:03 +08:00

output

[Bugfix] fix test_get_save_output_v1 (#4732)

2025-10-31 22:52:04 +08:00

platforms

【Hackathon 9th No.70】supplementary unit test for CPUPlatform and CUDAPlatform (#3580)

2025-08-29 10:34:05 +08:00

plugins

[Feature] support pool (#3827)

2025-09-22 14:09:09 +08:00

pooling

[Feature] support qwen3-embedding model load (#4202)

2025-09-23 00:14:35 -07:00

quantization

[BugFix]Fix load kv cache quant scale (#4077)

2025-09-12 17:44:03 +08:00

reasoning

[Cherry-Pick] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668) (#4737)

2025-10-31 23:27:21 +08:00

utils

【feature】support n parameter (#4273)

2025-10-17 20:51:59 +08:00

v1

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

conftest.py

[Executor] Default use CUDAGraph (#3594)

2025-10-21 14:25:45 +08:00

cov_pytest.ini

[CI] Handle unit test issues (#4483)

2025-10-20 10:13:21 +08:00

utils.py

[FDConfig]Remove max_model_len in FDConfig (#4350)

2025-10-11 14:04:17 +08:00