New models (#15861)

* 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>

docs/integrations/index.mdx

@@ -15,6 +15,7 @@ Coding assistants that can read, modify, and execute code in your projects.
 - [Droid](/integrations/droid)
 - [Goose](/integrations/goose)
 - [Pi](/integrations/pi)
+- [Poolside](/integrations/poolside)
 
 ## Assistants
 

docs/integrations/poolside.mdx

@@ -0,0 +1,54 @@
+---
+title: Poolside
+---
+
+Poolside is Poolside's software agent for the terminal, built for enterprise development workflows.
+
+## Install
+
+Install [Poolside](https://github.com/poolsideai/pool):
+
+## Usage with Ollama
+
+### Quick setup
+
+```shell
+ollama launch pool
+```
+
+### Run directly with a model
+
+```shell
+ollama launch pool --model kimi-k2.6:cloud
+```
+
+### Pass arguments through to Poolside
+
+Arguments after `--` are passed directly to Poolside:
+
+```shell
+ollama launch pool -- --help
+```
+
+## Manual setup
+
+Poolside connects to Ollama using the OpenAI-compatible API via environment variables.
+
+1. Set the environment variables:
+
+```shell
+export POOLSIDE_STANDALONE_BASE_URL=http://localhost:11434/v1
+export POOLSIDE_API_KEY=ollama
+```
+
+2. Run Poolside with an Ollama model:
+
+```shell
+pool -m kimi-k2.6:cloud
+```
+
+Or run with environment variables inline:
+
+```shell
+POOLSIDE_STANDALONE_BASE_URL=http://localhost:11434/v1 POOLSIDE_API_KEY=ollama pool -m kimi-k2.6:cloud
+```