luukunn e6804ba97d [Optimization]Streaming requests return complete special tokens. (#6998) ...

* return special token

* add completions

* update

* fix

* add prompt_token_ids&                        completion_token_ids=None,

* fix unite test

2026-03-26 09:49:43 +08:00

..

4cards_cases

[FDConfig] Reduce FD_CUSTOM_AR_MAX_SIZE_MB default from 64 to 8 (#6997)

2026-03-25 17:40:01 +08:00

EB_VL_Lite

…

golang_router

[CI] Add nightly workflow for golang_router tests and improve log handling (#6608)

2026-03-03 19:36:57 +08:00

Qwen3VL_RL

[Optimization] Accelerate Qwen3 QK RMSNorm via Fused Triton Kernel (#5880)

2026-01-12 05:10:21 -08:00

Qwen3VLMOE_RL

[Optimization] Accelerate Qwen3 QK RMSNorm via Fused Triton Kernel (#5880)

2026-01-12 05:10:21 -08:00

utils

[Feature] support v1 update/clear api for RL (#6761)

2026-03-25 19:18:46 +08:00

test_api_key.py

[CI] Optimize unittest and fix title format (#6464)

2026-02-11 20:48:56 +08:00

test_DeepSeek_V3_5layers_serving.py

…

test_EB_Lite_serving_R3.py

[RL][R3] Fix typo (#6046)

2026-01-22 15:46:34 +08:00

test_EB_Lite_serving.py

[Feature]Support reorder ids to split prefill and decodes (#5779)

2026-02-03 00:28:02 -08:00

test_EB_VL_Lite_serving.py

[Optimization]Streaming requests return complete special tokens. (#6998)

2026-03-26 09:49:43 +08:00

test_EB_VL_Lite_sot_serving.py

[Optimization]Streaming requests return complete special tokens. (#6998)

2026-03-26 09:49:43 +08:00

test_ernie_03b_pd_router_v1_ipc.py

…

test_ernie_03b_pd_router_v1_rdma_global_cache.py

[CI] Add test for pd and cache storage (#6876)

2026-03-19 10:38:27 +08:00

test_ernie_03b_pd_router_v1_rdma_tp1.py

[CI] Add test for pd and cache storage (#6876)

2026-03-19 10:38:27 +08:00

test_ernie_03b_pd_router_v1_rdma_tp2.py

[CI] Add test for pd and cache storage (#6876)

2026-03-19 10:38:27 +08:00

test_ernie_03b_router.py

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407)

2026-02-28 15:07:43 +08:00

test_ernie_21b_mtp.py

[Feature] use phi permute/unpermute & rm swiglu (#6361)

2026-03-12 02:01:57 -07:00

test_paddleocr_vl_serving.py

…

test_pd_reorder.py

[Others] Fix PD reorder for MTP (#6792)

2026-03-23 21:10:22 +08:00

test_Qwen2_5_VL_serving.py

[Feature] use phi permute/unpermute & rm swiglu (#6361)

2026-03-12 02:01:57 -07:00

test_Qwen2_5_VL_torch_serving.py

…

test_Qwen2-7B-Instruct_serving.py

…

test_Qwen3VL_serving.py

[Feature] use phi permute/unpermute & rm swiglu (#6361)

2026-03-12 02:01:57 -07:00

test_Qwen3VLMoe_serving.py

[Optimization] Enable BF16 gate computation for GLM and Qwen (#6457)

2026-02-26 21:08:46 -08:00