xc-llm-ascend

Files

Shanshan Shen 8326f15ecf [CustomOp] Register AscendSharedFusedMoE custom op (#2980 )

### What this PR does / why we need it?
Register `AscendSharedFusedMoE` custom op.

### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

`DeepSeek-V2-Lite` is a MoE model with shared experts.

Test:

```bash
vllm serve /root/.cache/modelscope/hub/models/deepseek-ai/DeepSeek-V2-Lite \
--trust-remote-code \
--enforce-eager \
--no-enable-prefix-caching \
--gpu-memory-utilization 0.95

curl -X POST http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "/root/.cache/modelscope/hub/models/deepseek-ai/DeepSeek-V2-Lite",
        "messages": [
            {"role": "user", "content": "介绍一下联通公司？"}
        ],
        "stream": false,
        "max_tokens": 100
    }'
```

Output:

```bash
中国联合网络通信集团有限公司（简称“中国联通”）于2009年1月6日在原中国网通和原中国联通的基础上合并组建而成，在国内31个省（自治区、直辖市）和境外多个国家和地区设有分支机构，是中国唯一一家在纽约、香港、上海三地同时上市的电信运营企业，连续多年入选“世界500强企业”。\n\n中国联通主要经营固定通信业务，移动通信业务，国内
```


- vLLM version: v0.10.2
- vLLM main:
486c5599e3

---------

Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Signed-off-by: shen-shanshan <467638484@qq.com>

2025-09-19 19:05:01 +08:00

moe

[Bugfix] Fix async copy bug under single expert scenario (#3005 )

2025-09-19 14:05:36 +08:00

__init__.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786 )

2025-09-13 11:58:52 +08:00

activation.py

[main] mlp weight prefetch in Qwen Dense Models (#2816 )

2025-09-11 21:20:09 +08:00

attention.py

Disaggregate prefill for kv cache register style (#950 )