EdoardoMosca commited on
Commit
466cacb
·
verified ·
1 Parent(s): c6904f7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -279,7 +279,7 @@ Both models [LiquidAI/LFM2.5-ColBERT-350M-GGUF](https://huggingface.co/LiquidAI/
279
 
280
  For large-scale production-grade enterprise deployments, we also experiment with an internal GPU stack to deliver extremely low-latency serving under high inbound load. We observe latencies as low as 1 ms.
281
 
282
- ![GPU serving latency](https://cdn-uploads.huggingface.co/production/uploads/63f389fda096536aeaae0a66/bCURXdLPs6wIamTIayit7.png)
283
 
284
  | Workload | Setup | p50 | p95 | p99 |
285
  | --- | --- | :-: | :-: | :-: |
 
279
 
280
  For large-scale production-grade enterprise deployments, we also experiment with an internal GPU stack to deliver extremely low-latency serving under high inbound load. We observe latencies as low as 1 ms.
281
 
282
+ ![GPU serving latency](https://cdn-uploads.huggingface.co/production/uploads/63f389fda096536aeaae0a66/WTdmKJ2LpG07-iAqXYGDe.png)
283
 
284
  | Workload | Setup | p50 | p95 | p99 |
285
  | --- | --- | :-: | :-: | :-: |