bukejiyu 3200a80de3 [v1 loader]support fp8 (#3593) ...

* support fp8

* update ci

2025-08-26 02:42:46 -07:00

..

ce

[CudaGraph][SOT] Add unit tests for splitting the static graph into piecewise graphs that support cuda_graph (#3590)

2025-08-26 11:25:04 +08:00

ci_use

[Feature] bad words support v1 scheduler and specifiy token ids (#3608)

2025-08-25 20:14:51 -07:00

distributed

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

e2e

[Feature] bad words support v1 scheduler and specifiy token ids (#3608)

2025-08-25 20:14:51 -07:00

entrypoints

Revert "[UnitTest][Copilot] Improve unit test coverage for entrypoints module…" (#3564)

2025-08-23 10:44:23 +08:00

graph_optimization

[CudaGraph][SOT] Add unit tests for splitting the static graph into piecewise graphs that support cuda_graph (#3590)

2025-08-26 11:25:04 +08:00

input

[Feature] Add Qwen25-VL Processor (#3501)

2025-08-22 16:49:42 +08:00

layers

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

logger

fix test name (#3493)

2025-08-22 23:43:47 +08:00

model_executor

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

model_loader

[v1 loader]support fp8 (#3593)

2025-08-26 02:42:46 -07:00

operators

[Feature][MTP]support new speculative decoding method named hybrid mtp with ngram (#3610)

2025-08-26 14:29:22 +08:00

plugins

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

utils

Unify server-side and model-side Config(Part-5) (#3497)

2025-08-21 19:00:21 +08:00

conftest.py

[V1 Loader] support weight_only (#3413)

2025-08-23 13:13:41 +08:00

cov_pytest.ini

Modify the existing coverage collection method (#3573)

2025-08-25 10:35:35 +08:00