mirror of
https://github.com/ollama/ollama.git
synced 2026-05-05 23:53:43 -05:00
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>
225 lines
5.2 KiB
JSON
225 lines
5.2 KiB
JSON
{
|
|
"$schema": "https://mintlify.com/docs.json",
|
|
"name": "Ollama",
|
|
"colors": {
|
|
"primary": "#000",
|
|
"light": "#b5b5b5",
|
|
"dark": "#000"
|
|
},
|
|
"favicon": "/images/favicon.png",
|
|
"logo": {
|
|
"light": "/images/logo.png",
|
|
"dark": "/images/logo-dark.png",
|
|
"href": "https://ollama.com"
|
|
},
|
|
"theme": "maple",
|
|
"background": {
|
|
"color": {
|
|
"light": "#ffffff",
|
|
"dark": "#000000"
|
|
}
|
|
},
|
|
"fonts": {
|
|
"family": "system-ui",
|
|
"heading": {
|
|
"family": "system-ui"
|
|
},
|
|
"body": {
|
|
"family": "system-ui"
|
|
}
|
|
},
|
|
"styling": {
|
|
"codeblocks": "system"
|
|
},
|
|
"contextual": {
|
|
"options": [
|
|
"copy"
|
|
]
|
|
},
|
|
"navbar": {
|
|
"links": [
|
|
{
|
|
"label": "Sign in",
|
|
"href": "https://ollama.com/signin"
|
|
}
|
|
],
|
|
"primary": {
|
|
"type": "button",
|
|
"label": "Download",
|
|
"href": "https://ollama.com/download"
|
|
}
|
|
},
|
|
"api": {
|
|
"playground": {
|
|
"display": "simple"
|
|
},
|
|
"examples": {
|
|
"languages": [
|
|
"curl"
|
|
]
|
|
}
|
|
},
|
|
"redirects": [
|
|
{
|
|
"source": "/openai",
|
|
"destination": "/api/openai-compatibility"
|
|
},
|
|
{
|
|
"source": "/api/openai",
|
|
"destination": "/api/openai-compatibility"
|
|
},
|
|
{
|
|
"source": "/api",
|
|
"destination": "/api/introduction"
|
|
},
|
|
{
|
|
"source": "/integrations/clawdbot",
|
|
"destination": "/integrations/openclaw"
|
|
}
|
|
],
|
|
"navigation": {
|
|
"tabs": [
|
|
{
|
|
"tab": "Documentation",
|
|
"groups": [
|
|
{
|
|
"group": "Get started",
|
|
"pages": [
|
|
"index",
|
|
"quickstart",
|
|
"/cloud"
|
|
]
|
|
},
|
|
{
|
|
"group": "Capabilities",
|
|
"pages": [
|
|
"/capabilities/streaming",
|
|
"/capabilities/thinking",
|
|
"/capabilities/structured-outputs",
|
|
"/capabilities/vision",
|
|
"/capabilities/embeddings",
|
|
"/capabilities/tool-calling",
|
|
"/capabilities/web-search"
|
|
]
|
|
},
|
|
{
|
|
"group": "Integrations",
|
|
"pages": [
|
|
"/integrations/index",
|
|
{
|
|
"group": "Assistants",
|
|
"expanded": true,
|
|
"pages": [
|
|
"/integrations/openclaw",
|
|
"/integrations/hermes"
|
|
]
|
|
},
|
|
{
|
|
"group": "Coding",
|
|
"expanded": true,
|
|
"pages": [
|
|
"/integrations/claude-code",
|
|
"/integrations/codex",
|
|
"/integrations/copilot-cli",
|
|
"/integrations/opencode",
|
|
"/integrations/droid",
|
|
"/integrations/goose",
|
|
"/integrations/pi",
|
|
"/integrations/poolside"
|
|
]
|
|
},
|
|
{
|
|
"group": "IDEs & Editors",
|
|
"expanded": true,
|
|
"pages": [
|
|
"/integrations/cline",
|
|
"/integrations/jetbrains",
|
|
"/integrations/roo-code",
|
|
"/integrations/vscode",
|
|
"/integrations/xcode",
|
|
"/integrations/zed"
|
|
]
|
|
},
|
|
{
|
|
"group": "Chat & RAG",
|
|
"pages": [
|
|
"/integrations/onyx"
|
|
]
|
|
},
|
|
{
|
|
"group": "Automation",
|
|
"pages": [
|
|
"/integrations/n8n"
|
|
]
|
|
},
|
|
{
|
|
"group": "Notebooks",
|
|
"pages": [
|
|
"/integrations/marimo"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"group": "More information",
|
|
"pages": [
|
|
"/cli",
|
|
{
|
|
"group": "Assistant Sandboxing",
|
|
"pages": [
|
|
"/integrations/nemoclaw"
|
|
]
|
|
},
|
|
"/modelfile",
|
|
"/context-length",
|
|
"/linux",
|
|
"/macos",
|
|
"/windows",
|
|
"/docker",
|
|
"/import",
|
|
"/faq",
|
|
"/gpu",
|
|
"/troubleshooting"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tab": "API Reference",
|
|
"openapi": "/openapi.yaml",
|
|
"groups": [
|
|
{
|
|
"group": "API Reference",
|
|
"pages": [
|
|
"/api/introduction",
|
|
"/api/authentication",
|
|
"/api/streaming",
|
|
"/api/usage",
|
|
"/api/errors",
|
|
"/api/openai-compatibility",
|
|
"/api/anthropic-compatibility"
|
|
]
|
|
},
|
|
{
|
|
"group": "Endpoints",
|
|
"pages": [
|
|
"POST /api/generate",
|
|
"POST /api/chat",
|
|
"POST /api/embed",
|
|
"GET /api/tags",
|
|
"GET /api/ps",
|
|
"POST /api/show",
|
|
"POST /api/create",
|
|
"POST /api/copy",
|
|
"POST /api/pull",
|
|
"POST /api/push",
|
|
"DELETE /api/delete",
|
|
"GET /api/version"
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
}
|