RAM 5b22e5dfe7 [RL] R3 Support Fused Put the Routing of All Layers (#6099) ...

* fused put routing

* fix bug

* [draft commit]dynamic dtype

* fix async put & numpy bug

* fix unit8 test case

2026-02-03 04:13:16 -08:00

..

4cards_cases

[UT] Add GLM E2E tests for non-MTP and MTP (#6163)

2026-01-23 10:34:29 +08:00

EB_VL_Lite

[CI] Allow occasional distributed worker exit_code (#5341)

2025-12-03 10:56:59 +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

[RL] R3 Support Fused Put the Routing of All Layers (#6099)

2026-02-03 04:13:16 -08:00

test_api_key.py

[Docs] Add License in Unittest (#4957)

2025-11-12 10:44:09 +08:00

test_DeepSeek_V3_5layers_serving.py

fix: ci port conflict (#4840)

2025-11-06 11:56:17 +08:00

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

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

test_EB_VL_Lite_sot_serving.py

[Graph Optimization] remove static_op_get_block_shape_and_split_kv_block from cudagraph (#6081)

2026-01-20 14:05:18 +08:00

test_ernie_03b_pd_router_v0_ipc.py

[PD Disaggregation] Unify the disaggregation info and the pd communication (#5438)

2025-12-09 14:44:59 +08:00

test_ernie_03b_pd_router_v1_ipc.py

Reduce timeout in unittest (#5366)

2025-12-04 13:19:02 +08:00

test_ernie_03b_pd_router_v1_rdma_tp1.py

Reduce timeout in unittest (#5366)

2025-12-04 13:19:02 +08:00

test_ernie_03b_pd_router_v1_rdma_tp2.py

Reduce timeout in unittest (#5366)

2025-12-04 13:19:02 +08:00

test_ernie_03b_router.py

Reduce timeout in unittest (#5366)

2025-12-04 13:19:02 +08:00

test_ernie_21b_mtp.py

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

test_paddleocr_vl_serving.py

[Graph Optimization][CINN] Use CINN in PaddleOCR-VL ViT part (#5223)

2025-12-09 14:37:00 +08:00

test_Qwen2_5_VL_serving.py

[Feature] Unify fp8 block_wise quant ops (#5991)

2026-01-15 05:50:37 -08:00

test_Qwen2_5_VL_torch_serving.py

fix: ci port conflict (#4840)

2025-11-06 11:56:17 +08:00

test_Qwen2-7B-Instruct_serving.py

fix: ci port conflict (#4840)

2025-11-06 11:56:17 +08:00

test_Qwen3VL_serving.py

[Models] Qwen3VL and Qwen3VL-Moe CUDA graph Support (#5962)

2026-01-09 17:09:02 +08:00

test_Qwen3VLMoe_serving.py

[Models] Qwen3VL and Qwen3VL-Moe CUDA graph Support (#5962)

2026-01-09 17:09:02 +08:00