87288ced4f
* mlx: add laguna model support * convert: support fp8 safetensors import Decode HF F8_E4M3 safetensors with block scale companions into GGUF-supported tensor types, and record which output tensors came from FP8 source weights. Use that source-precision metadata during create quantization: default FP8-sourced GGUFs to Q8_0, keep non-FP8 tensors at their original precision for Q8_0, and promote non-FP8 quantizable tensors to Q8_0 for Q4_K requests. * ggml: add laguna model support * server: preserve generate logprobs with builtin parsers Generate requests were dropping logprob-only chunks whenever a builtin parser buffered visible content. Chat already handled this case, but generate only forwarded chunks with visible response, thinking, or tool-call output. Keep generate chunks that carry logprobs even when the builtin parser has not flushed visible content yet, and add a regression test that exercises the behavior with a generic thinking parser. * review comments - perf improvements * ggml: implement nemotron 3 nano omni * add poolside integration * update poolside doc * adapt to new cache setup * fix test * fix test --------- Co-authored-by: Eva Ho <hoyyeva@gmail.com>
104 lines
3.0 KiB
Go
104 lines
3.0 KiB
Go
package renderers
|
|
|
|
import (
|
|
"fmt"
|
|
|
|
"github.com/ollama/ollama/api"
|
|
)
|
|
|
|
type Renderer interface {
|
|
Render(messages []api.Message, tools []api.Tool, think *api.ThinkValue) (string, error)
|
|
}
|
|
|
|
type (
|
|
RendererConstructor func() Renderer
|
|
RendererRegistry struct {
|
|
renderers map[string]RendererConstructor
|
|
}
|
|
)
|
|
|
|
// RenderImgTags is a global flag that tells renderers to use [img] tags
|
|
// for images. This is set by the Ollama server package on init, or left as
|
|
// false for other environments where renderers are used
|
|
var RenderImgTags bool
|
|
|
|
func (r *RendererRegistry) Register(name string, renderer RendererConstructor) {
|
|
r.renderers[name] = renderer
|
|
}
|
|
|
|
var registry = RendererRegistry{
|
|
renderers: make(map[string]RendererConstructor),
|
|
}
|
|
|
|
func Register(name string, renderer RendererConstructor) {
|
|
registry.Register(name, renderer)
|
|
}
|
|
|
|
func RenderWithRenderer(name string, msgs []api.Message, tools []api.Tool, think *api.ThinkValue) (string, error) {
|
|
renderer := rendererForName(name)
|
|
if renderer == nil {
|
|
return "", fmt.Errorf("unknown renderer %q", name)
|
|
}
|
|
return renderer.Render(msgs, tools, think)
|
|
}
|
|
|
|
func rendererForName(name string) Renderer {
|
|
if constructor, ok := registry.renderers[name]; ok {
|
|
return constructor()
|
|
}
|
|
switch name {
|
|
case "qwen3-coder":
|
|
renderer := &Qwen3CoderRenderer{}
|
|
return renderer
|
|
case "qwen3-vl-instruct":
|
|
renderer := &Qwen3VLRenderer{isThinking: false, useImgTags: RenderImgTags}
|
|
return renderer
|
|
case "qwen3-vl-thinking":
|
|
renderer := &Qwen3VLRenderer{isThinking: true, useImgTags: RenderImgTags}
|
|
return renderer
|
|
case "qwen3.5":
|
|
renderer := &Qwen35Renderer{isThinking: true, emitEmptyThinkOnNoThink: true, useImgTags: RenderImgTags}
|
|
return renderer
|
|
case "cogito":
|
|
renderer := &CogitoRenderer{isThinking: true}
|
|
return renderer
|
|
case "deepseek3.1":
|
|
renderer := &DeepSeek3Renderer{IsThinking: true, Variant: Deepseek31}
|
|
return renderer
|
|
case "olmo3":
|
|
renderer := &Olmo3Renderer{UseExtendedSystemMessage: false}
|
|
return renderer
|
|
case "olmo3.1":
|
|
renderer := &Olmo3Renderer{UseExtendedSystemMessage: true}
|
|
return renderer
|
|
case "olmo3-think":
|
|
// Used for Olmo-3-7B-Think and Olmo-3.1-32B-Think (same template)
|
|
renderer := &Olmo3ThinkRenderer{Variant: Olmo31Think}
|
|
return renderer
|
|
case "olmo3-32b-think":
|
|
// Used for Olmo-3-32B-Think
|
|
renderer := &Olmo3ThinkRenderer{Variant: Olmo3Think32B}
|
|
return renderer
|
|
case "nemotron-3-nano":
|
|
return &Nemotron3NanoRenderer{}
|
|
case "gemma4", "gemma4-small":
|
|
return &Gemma4Renderer{useImgTags: RenderImgTags}
|
|
case "gemma4-large":
|
|
return &Gemma4Renderer{useImgTags: RenderImgTags, emptyBlockOnNothink: true}
|
|
case "functiongemma":
|
|
return &FunctionGemmaRenderer{}
|
|
case "glm-4.7":
|
|
return &GLM47Renderer{}
|
|
case "glm-ocr":
|
|
return &GlmOcrRenderer{useImgTags: RenderImgTags}
|
|
case "lfm2":
|
|
return &LFM2Renderer{IsThinking: false, useImgTags: RenderImgTags}
|
|
case "lfm2-thinking":
|
|
return &LFM2Renderer{IsThinking: true, useImgTags: RenderImgTags}
|
|
case "laguna":
|
|
return &LagunaRenderer{}
|
|
default:
|
|
return nil
|
|
}
|
|
}
|