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
examples/disaggregated_prefill_v1/load_balance_proxy_layerwise_server_example.py
View File

@@ -178,7 +178,7 @@ class ProxyState:
# No lock needed - atomic operation
self.prefillers[server_idx].aborted_requests.add(request_id)
def aquire_aborted_prefiller_requests(self, server_idx: int): # Changed to synchronous
def acquire_aborted_prefiller_requests(self, server_idx: int): # Changed to synchronous
"""
Get the set of aborted requests and clear it.
This is used to release kv cache in prefiller node.
@@ -325,7 +325,7 @@ async def send_request_to_service(
max_retries: int = 3,
base_delay: float = 0.2,
):
proxy_state.aquire_aborted_prefiller_requests(prefiller_id)
proxy_state.acquire_aborted_prefiller_requests(prefiller_id)
req_data = req_data.copy()
req_data["stream"] = False
req_data["max_tokens"] = 1

4
examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py
View File

@@ -241,7 +241,7 @@ class ProxyState:
return
self.prefillers[server_idx].aborted_requests.add(request_id)
def aquire_aborted_prefiller_requests(self, server_idx: int): # Changed to synchronous
def acquire_aborted_prefiller_requests(self, server_idx: int): # Changed to synchronous
"""
Get the set of aborted requests and clear it.
This is used to release kv cache in prefiller node.
@@ -582,7 +582,7 @@ async def send_request_to_service(
max_retries: int = 3,
base_delay: float = 0.2,
):
aborted_requests = proxy_state.aquire_aborted_prefiller_requests(prefiller_id)
aborted_requests = proxy_state.acquire_aborted_prefiller_requests(prefiller_id)
req_data = req_data.copy()
req_data["kv_transfer_params"] = {
"do_remote_decode": True,