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

4
vllm_ascend/spec_decode/eagle_proposer.py
View File

@@ -941,7 +941,7 @@ class EagleProposer(VllmEagleProposer):
# [0, 1, 2, 3, 4, 5, 6, 7, 8] ->
# [0, 1, 0, 1, 2, 3, 0, 1, 2]
# _r1_ ____r2____ ___r3__
token_offests = self.token_arange_np[:total_num_tokens] - new_query_start_locs_expanded
token_offsets = self.token_arange_np[:total_num_tokens] - new_query_start_locs_expanded
# Expand starting positions to match token pattern
# [0, q1, q1 + q2] ->
@@ -952,7 +952,7 @@ class EagleProposer(VllmEagleProposer):
# [0, 1, // req 1
# q1 + 0, q1 + 1, q1 + 2, q1 + 3, // req 2
# q1 + q2 + 0, q1 + q2 + 1, q1 + q2 + 2] // req 3
token_indices_np = token_offests + old_query_start_locs_expanded
token_indices_np = token_offsets + old_query_start_locs_expanded
token_indices = torch.from_numpy(token_indices_np).to(device, non_blocking=True)
common_attn_metadata.slot_mapping[: token_indices.shape[0]].copy_(