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

[CI]Fixed the spell check function in typos.toml (#6753)

Browse Source 
### What this PR does / why we need it?
The incorrect regular expression syntax `.*[UE4M3|ue4m3].*` actually
ignores all words containing any of the following characters: `u, e, 4,
m, 3, |`

```yaml
extend-ignore-identifiers-re = [".*Unc.*", ".*_thw",
    ".*UE8M0.*", ".*[UE4M3|ue4m3].*", ".*eles.*", ".*fo.*", ".*ba.*",
    ".*ot.*", ".*[Tt]h[rR].*"]
```
===fix===>
```yaml
extend-ignore-identifiers-re = [".*Unc.*", ".*_thw",
    ".*UE8M0.*", ".*(UE4M3|ue4m3]).*", ".*eles.*", ".*fo.*", ".*ba.*",
    ".*ot.*", ".*[Tt]h[rR].*"]
```

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

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
9562912cea

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2026-02-14 11:57:26 +08:00
committed by GitHub
parent 64aea60f2e
commit e2237819a9
31 changed files with 79 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm_ascend/ascend_config.py
View File

@@ -144,14 +144,14 @@ class AscendConfig:
if os.getenv("VLLM_ASCEND_ENABLE_PREFETCH_MLP", "0") == "1":
MAX_PREFETCH_WEIGHT_SIZE: int = 18 * 1024 * 1024
gate_up_prefetch_size = int(os.getenv("VLLM_ASCEND_MLP_GATE_UP_PREFETCH_SIZE", MAX_PREFETCH_WEIGHT_SIZE))
down_prefetch_szie = int(os.getenv("VLLM_ASCEND_MLP_DOWN_PREFETCH_SIZE", MAX_PREFETCH_WEIGHT_SIZE))
down_prefetch_size = int(os.getenv("VLLM_ASCEND_MLP_DOWN_PREFETCH_SIZE", MAX_PREFETCH_WEIGHT_SIZE))
self.weight_prefetch_config.set_mlp_pre_version_compatibale_config(
gate_up_prefetch_size, down_prefetch_szie
gate_up_prefetch_size, down_prefetch_size
)
logger.info_once(
f"MLP weight prefetch enabled from env variable VLLM_ASCEND_ENABLE_PREFETCH_MLP."
f"gate_up_prefetch_size={gate_up_prefetch_size}, "
f"down_prefetch_szie={down_prefetch_szie}."
f"down_prefetch_size={down_prefetch_size}."
)
warnings.warn(
"VLLM_ASCEND_ENABLE_PREFETCH_MLP is deprecated and will be removed in a v0.16.0 version. "