Revert "runner: move harmony to runner (#12052)"
release / setup-environment (push) Has been cancelled
release / windows-depends (amd64, -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma", https:/… (push) Has been cancelled
release / windows-depends (amd64, ["cudart" "nvcc" "cublas" "cublas_dev" "crt" "nvvm" "nvptxcompiler"], 13.0, , https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe, windows, CUDA 13, cuda_v13) (push) Has been cancelled
release / windows-depends (amd64, ["cudart" "nvcc" "cublas" "cublas_dev"], 12.8, , https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_571.96_windows.exe, windows, CUDA 12, cuda_v12) (push) Has been cancelled
release / windows-depends (amd64, windows, CPU) (push) Has been cancelled
release / darwin-build (amd64, darwin) (push) Has been cancelled
release / darwin-build (arm64, darwin) (push) Has been cancelled
release / windows-build (amd64, windows) (push) Has been cancelled
release / windows-build (arm64, windows) (push) Has been cancelled
release / linux-build (amd64, linux, archive) (push) Has been cancelled
release / linux-build (amd64, linux, rocm) (push) Has been cancelled
release / linux-build (arm64, linux, archive) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS , linux) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS FLAVOR=rocm , linux, -rocm) (push) Has been cancelled
release / docker-build-push (arm64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS , linux) (push) Has been cancelled
release / docker-merge-push () (push) Has been cancelled
release / docker-merge-push (-rocm) (push) Has been cancelled
release / trigger (push) Has been cancelled

This reverts commit 1a558f98e2.
This commit is contained in:
jmorganca
2025-09-12 13:32:30 -07:00
committed by Jeffrey Morgan
parent 9d56e63dbf
commit 92b96d54ef
6 changed files with 337 additions and 369 deletions
+1 -54
View File
@@ -29,7 +29,6 @@ import (
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/envconfig"
"github.com/ollama/ollama/harmony"
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/logutil"
"github.com/ollama/ollama/ml"
@@ -781,14 +780,6 @@ func (s *Server) completion(w http.ResponseWriter, r *http.Request) {
return
}
var harmonyMessageHandler *harmony.HarmonyMessageHandler
var harmonyToolParser *harmony.HarmonyToolCallAccumulator
if req.UseHarmony {
harmonyMessageHandler = harmony.NewHarmonyMessageHandler()
harmonyMessageHandler.HarmonyParser.AddImplicitStartOrPrefill(req.PrefillString)
harmonyToolParser = harmonyMessageHandler.CreateToolParser()
}
if req.Options == nil {
opts := api.DefaultOptions()
req.Options = &opts
@@ -871,9 +862,6 @@ func (s *Server) completion(w http.ResponseWriter, r *http.Request) {
http.Error(w, "could not find an available sequence", http.StatusInternalServerError)
return
}
var lastToken string
tokenRepeat := 0
const tokenRepeatLimit = 30
for {
select {
@@ -882,27 +870,8 @@ func (s *Server) completion(w http.ResponseWriter, r *http.Request) {
return
case content, ok := <-seq.responses:
if ok {
if strings.TrimSpace(content) == lastToken {
tokenRepeat++
}
if tokenRepeat == tokenRepeatLimit {
http.Error(w, "token repeat limit reached", http.StatusInternalServerError)
seq.doneReason = llm.DoneReasonTokenRepeatLimit
close(seq.quit)
return
}
lastToken = strings.TrimSpace(content)
var thinking string
if harmonyMessageHandler != nil {
var toolContent string
content, thinking, toolContent = harmonyMessageHandler.AddContent(content, harmonyToolParser)
harmonyToolParser.Add(toolContent)
}
if err := json.NewEncoder(w).Encode(&llm.CompletionResponse{
Content: content,
Thinking: thinking,
Content: content,
}); err != nil {
http.Error(w, fmt.Sprintf("failed to encode response: %v", err), http.StatusInternalServerError)
close(seq.quit)
@@ -911,29 +880,7 @@ func (s *Server) completion(w http.ResponseWriter, r *http.Request) {
flusher.Flush()
} else {
var toolCalls []api.ToolCall
if harmonyMessageHandler != nil {
// these tools still need to be transformed to the original function name
toolName, toolContent := harmonyToolParser.Drain()
if toolName != nil {
*toolName = strings.TrimPrefix(*toolName, "functions.")
var args api.ToolCallFunctionArguments
if err := json.Unmarshal([]byte(toolContent), &args); err != nil {
http.Error(w, fmt.Sprintf("failed to unmarshal tool call function arguments: %v", err), http.StatusInternalServerError)
close(seq.quit)
return
}
toolCalls = append(toolCalls, api.ToolCall{
Function: api.ToolCallFunction{
Name: *toolName,
Arguments: args,
},
})
}
}
if err := json.NewEncoder(w).Encode(&llm.CompletionResponse{
ToolCalls: toolCalls,
Done: true,
DoneReason: seq.doneReason,
PromptEvalCount: seq.numPromptInputs,