Canlin GuoandHongsheng Liu af11b02081 [Minor][Refactor] Pass seq_token_counts explicitly (#1425) ...

Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-02-24 14:10:00 +08:00

..

layers

Dev/rebase v0.15.0 (#1159)

2026-02-03 12:24:45 +08:00

model_loader

[Fix]Ensure HuggingFace downloads complete before initialization. (#1213)

2026-02-10 16:05:12 +08:00

models

[Minor][Refactor] Pass seq_token_counts explicitly (#1425)

2026-02-24 14:10:00 +08:00

stage_configs

[Feature] vLLM-Omni RDMA connector (#1019)

2026-02-24 11:13:52 +08:00

stage_input_processors

[Feature] : Support disaggregated inference pipeline for Qwen3_TTS (#1161)

2026-02-21 07:36:44 +08:00

__init__.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

custom_process_mixin.py

[Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (#458)

2025-12-24 13:26:33 +00:00