mirror of
https://github.com/ollama/ollama.git
synced 2026-04-17 15:53:27 +02:00
mlx: Remove peak memory from the API
This is still in flux so it is better to just log it for now.
This commit is contained in:
@@ -558,7 +558,6 @@ func (s *Server) GenerateHandler(c *gin.Context) {
|
||||
PromptEvalDuration: cr.PromptEvalDuration,
|
||||
EvalCount: cr.EvalCount,
|
||||
EvalDuration: cr.EvalDuration,
|
||||
PeakMemory: cr.PeakMemory,
|
||||
},
|
||||
Logprobs: toAPILogprobs(cr.Logprobs),
|
||||
}
|
||||
@@ -2317,7 +2316,6 @@ func (s *Server) ChatHandler(c *gin.Context) {
|
||||
PromptEvalDuration: r.PromptEvalDuration,
|
||||
EvalCount: r.EvalCount,
|
||||
EvalDuration: r.EvalDuration,
|
||||
PeakMemory: r.PeakMemory,
|
||||
},
|
||||
Logprobs: toAPILogprobs(r.Logprobs),
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user