mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

embed: cleanup (#12299)

Browse Source 
* cleanup

* use pooling.TypeNone

* pooling test
This commit is contained in:
Michael Yang
2025-09-16 09:48:42 -07:00
committed by GitHub
parent a1cff89b30
commit c253433d68
6 changed files with 104 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
runner/ollamarunner/runner.go
View File

@@ -11,7 +11,6 @@ import (
"image"
"log"
"log/slog"
"math"
"net"
"net/http"
"os"
@@ -32,6 +31,7 @@ import (
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/logutil"
"github.com/ollama/ollama/ml"
"github.com/ollama/ollama/ml/nn/pooling"
"github.com/ollama/ollama/model"
"github.com/ollama/ollama/model/input"
"github.com/ollama/ollama/runner/common"
@@ -405,7 +405,7 @@ func (s *Server) removeSequence(seqIndex int, reason llm.DoneReason) {
func (s *Server) run(ctx context.Context) {
s.ready.Wait()
supportsAsync := s.model.Backend().Config().Uint("pooling_type", math.MaxUint32) == math.MaxUint32
supportsAsync := pooling.Type(s.model.Backend().Config().Uint("pooling_type")) == pooling.TypeNone
var activeBatch batchState
for {
@@ -900,7 +900,7 @@ func (s *Server) completion(w http.ResponseWriter, r *http.Request) {
}
func (s *Server) embeddings(w http.ResponseWriter, r *http.Request) {
if s.model.Backend().Config().Uint("pooling_type", math.MaxUint32) == math.MaxUint32 {
if pooling.Type(s.model.Backend().Config().Uint("pooling_type")) == pooling.TypeNone {
http.Error(w, "this model does not support embeddings", http.StatusNotImplemented)
return
}