xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-04 22:35:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V0][Metrics] Remove unimplemented vllm:tokens_total (#14134)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin 2025-03-03 17:50:22 +00:00 committed by GitHub
parent 91373a0d15
commit c41d27156b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/engine/metrics.py
View File

@ -115,10 +115,6 @@ class Metrics:
name="vllm:generation_tokens_total", name="vllm:generation_tokens_total",
documentation="Number of generation tokens processed.", documentation="Number of generation tokens processed.",
labelnames=labelnames) labelnames=labelnames)
self.counter_tokens = self._counter_cls(
name="vllm:tokens_total",
documentation="Number of prefill plus generation tokens processed.",
labelnames=labelnames)
buckets = [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8096] buckets = [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8096]
if not vllm_config.model_config.enforce_eager: if not vllm_config.model_config.enforce_eager:
buckets = vllm_config.compilation_config.\ buckets = vllm_config.compilation_config.\