biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] feat:add engine v1 tracing (#20372)

Browse Source 
Signed-off-by: Mu Huai <tianbowen.tbw@antgroup.com>
Signed-off-by: Ye Zhang <zhysishu@gmail.com>
Signed-off-by: RichardoMu <44485717+RichardoMrMu@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Mu Huai <tianbowen.tbw@antgroup.com>
Co-authored-by: Ye Zhang <zhysishu@gmail.com>
Co-authored-by: Benjamin Bartels <benjamin@bartels.dev>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: 瑜琮 <ly186375@antfin.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
This commit is contained in:
RichardoMu
2025-09-12 08:10:39 +08:00
committed by GitHub
parent 2e6bc46821
commit 40b6c9122b
12 changed files with 253 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/arg_utils.py
View File

@@ -1491,12 +1491,6 @@ class EngineArgs:
recommend_to_remove=False)
return False
# No OTLP observability so far.
if (self.otlp_traces_endpoint or self.collect_detailed_traces):
_raise_or_fallback(feature_name="--otlp-traces-endpoint",
recommend_to_remove=False)
return False
# V1 supports N-gram, Medusa, and Eagle speculative decoding.
if (self.speculative_config is not None
and self.speculative_config.get("method") == "draft_model"):