wangxiyuan 1fce70a2fb [Model] Support common fused moe ops for moe model, such as Qwen3Moe (#709) ...

vllm-ascend now only support moe for deepseek. We should add common moe
support back

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-04-28 21:57:01 +08:00

..

__init__.py

[Model] Support common fused moe ops for moe model, such as Qwen3Moe (#709)

2025-04-28 21:57:01 +08:00

activation.py

[CI]Add model basic accuracy test(Qwen2.5-0.5B-Instruct) (#460)

2025-04-17 14:59:56 +08:00

attention.py

port deepseekv2 and mtp to main branch (#429)

2025-04-19 17:38:18 +08:00

cache.py

port deepseekv2 and mtp to main branch (#429)

2025-04-19 17:38:18 +08:00

common_fused_moe.py

[Model] Support common fused moe ops for moe model, such as Qwen3Moe (#709)

2025-04-28 21:57:01 +08:00

fused_moe.py

support deepseek quant & mix-parallel with graphmode (#585)

2025-04-23 16:23:25 +08:00

layernorm.py

[CI]Add model basic accuracy test(Qwen2.5-0.5B-Instruct) (#460)

2025-04-17 14:59:56 +08:00

rotary_embedding.py

Add note for deepseek related docs and remove unnecessary comments (#590)

2025-04-22 09:59:09 +08:00

vocab_parallel_embedding.py

port deepseekv2 and mtp to main branch (#429)

2025-04-19 17:38:18 +08:00