lizexu123 525be243e7 [Bug fix] Fixed the garbled text issues in Qwen3-8B (#2737) ...

* fix qwen3.py

* update

* update lm_head tie_word_embeddings

* update tie_word_embeddings

* fix

* fix tie_word_embedding not in config.json

---------

Co-authored-by: lizexu <lizexu@baidu.com>

2025-07-07 23:15:27 -07:00

..

__init__.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

eplb.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

experts_manager.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

forward_meta.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

gcu_model_runner.py

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

gcu_worker.py

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

gpu_model_runner.py

support chunk_prefill in MTP (#2705)

2025-07-04 11:55:48 +08:00

gpu_worker.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

iluvatar_model_runner.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

iluvatar_worker.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

model_runner_base.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

output.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

utils.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

vl_gpu_model_runner.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

vl_model_runner_base.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

vl_worker_process.py

[LLM] support multi node deploy (#2708)

2025-07-06 10:33:51 +08:00

worker_base.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

worker_process.py

[Bug fix] Fixed the garbled text issues in Qwen3-8B (#2737)

2025-07-07 23:15:27 -07:00

xpu_model_runner.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

xpu_worker.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00