EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[2/N][Pangu][MoE] Remove Pangu Related Code (#5130)

Browse Source 
### What this PR does / why we need it?
Remove Pangu Related Code

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
e2e & ut

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: weichen <calvin_zhu0210@outlook.com>
This commit is contained in:
weichen
2025-12-19 09:00:07 +08:00
committed by GitHub
parent 1b47fca0e8
commit ca6f631cba
11 changed files with 8 additions and 1444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/source/user_guide/configuration/additional_config.md
View File

@@ -30,8 +30,7 @@ The following table lists additional configuration options available in vLLM Asc
| `finegrained_tp_config` | dict | `{}` | Configuration options for module tensor parallelism |
| `weight_prefetch_config` | dict | `{}` | Configuration options for weight prefetch |
| `refresh` | bool | `false` | Whether to refresh global Ascend configuration content. This is usually used by rlhf or ut/e2e test case. |
| `expert_map_path` | str | `None` | When using expert load balancing for an MoE model, an expert map path needs to be passed in. |
| `kv_cache_dtype` | str | `None` | When using the KV cache quantization method, KV cache dtype needs to be set, currently only int8 is supported. |
| `expert_map_path` | str | `None` | When using expert load balancing for an MoE model, an expert map path needs to be passed in. | |
| `enable_shared_expert_dp` | bool | `False` | When the expert is shared in DP, it delivers better performance but consumes more memory. Currently only DeepSeek series models are supported. |
| `lmhead_tensor_parallel_size` | int | `None` | The custom tensor parallel size of lmhead. Restriction: Can only be used when tensor_parallel=1 |
| `oproj_tensor_parallel_size` | int | `None` | The custom tensor parallel size of oproj. |