highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-25 20:51:11 +02:00
Code Issues Packages Projects Releases Wiki Activity

API/CLI context enhancements (#11331)

Browse Source 
* API: expose context size of loaded models

* CLI: add context UX

This adds a column in the ps output to show the models context size.
This commit is contained in:
Daniel Hiltgen
2025-07-08 11:59:06 -07:00
committed by GitHub
parent 43107b15b9
commit 34088dbcfb
3 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
api/types.go
View File

@@ -468,13 +468,14 @@ type ListModelResponse struct {
// ProcessModelResponse is a single model description in [ProcessResponse].
type ProcessModelResponse struct {
Name string `json:"name"`
Model string `json:"model"`
Size int64 `json:"size"`
Digest string `json:"digest"`
Details ModelDetails `json:"details,omitempty"`
ExpiresAt time.Time `json:"expires_at"`
SizeVRAM int64 `json:"size_vram"`
Name string `json:"name"`
Model string `json:"model"`
Size int64 `json:"size"`
Digest string `json:"digest"`
Details ModelDetails `json:"details,omitempty"`
ExpiresAt time.Time `json:"expires_at"`
SizeVRAM int64 `json:"size_vram"`
ContextLength int `json:"context_length"`
}
type TokenResponse struct {

5
cmd/cmd.go
View File

@@ -583,12 +583,13 @@ func ListRunningHandler(cmd *cobra.Command, args []string) error {
} else {
until = format.HumanTime(m.ExpiresAt, "Never")
}
data = append(data, []string{m.Name, m.Digest[:12], format.HumanBytes(m.Size), procStr, until})
ctxStr := strconv.Itoa(m.ContextLength)
data = append(data, []string{m.Name, m.Digest[:12], format.HumanBytes(m.Size), procStr, ctxStr, until})
}
}
table := tablewriter.NewWriter(os.Stdout)
table.SetHeader([]string{"NAME", "ID", "SIZE", "PROCESSOR", "UNTIL"})
table.SetHeader([]string{"NAME", "ID", "SIZE", "PROCESSOR", "CONTEXT", "UNTIL"})
table.SetHeaderAlignment(tablewriter.ALIGN_LEFT)
table.SetAlignment(tablewriter.ALIGN_LEFT)
table.SetHeaderLine(false)

3
server/routes.go
View File

@@ -1404,6 +1404,9 @@ func (s *Server) PsHandler(c *gin.Context) {
Details: modelDetails,
ExpiresAt: v.expiresAt,
}
if v.Options != nil {
mr.ContextLength = v.Options.NumCtx / v.numParallel
}
// The scheduler waits to set expiresAt, so if a model is loading it's
// possible that it will be set to the unix epoch. For those cases, just
// calculate the time w/ the sessionDuration instead.