From 0db7da96cce0c6263ef3459ecc4f233c7b4c2fff Mon Sep 17 00:00:00 2001
From: Shine1i <wasimysdev@gmail.com>
Date: Mon, 16 Feb 2026 21:33:24 +0100
Subject: [PATCH] feat: support disabling top-k sampling with -1 and
 standardize normalization logic

- Updated top-k parameter range to accept -1 in models and frontend.
- Added utility to normalize top-k for backend compatibility.
---
 studio/backend/core/inference/inference.py                | 6 ++++++
 studio/backend/models/inference.py                        | 4 ++--
 studio/frontend/src/features/chat/chat-settings-sheet.tsx | 2 +-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/studio/backend/core/inference/inference.py b/studio/backend/core/inference/inference.py
index 38394f6f33..31e23f5370 100644
--- a/studio/backend/core/inference/inference.py
+++ b/studio/backend/core/inference/inference.py
@@ -45,6 +45,11 @@ class InferenceBackend:
 
         logger.info(f"InferenceBackend initialized on {self.device}")
 
+    @staticmethod
+    def _normalize_top_k(top_k: int) -> int:
+        # API supports -1 as "disable top-k"; transformers expects 0 to disable.
+        return 0 if top_k < 0 else top_k
+
     def load_model(self,
                    config: ModelConfig,
                    max_seq_length: int = 2048,
@@ -560,6 +565,7 @@ class InferenceBackend:
         model_info = self.models[self.active_model_name]
         is_vision = model_info.get("is_vision", False)
         tokenizer = model_info.get("tokenizer") or model_info.get("processor")
+        top_k = self._normalize_top_k(top_k)
 
         if is_vision:
             # Vision model generation
diff --git a/studio/backend/models/inference.py b/studio/backend/models/inference.py
index 1b661047ae..d2d98d7944 100644
--- a/studio/backend/models/inference.py
+++ b/studio/backend/models/inference.py
@@ -30,7 +30,7 @@ class GenerateRequest(BaseModel):
     system_prompt: str = Field("You are a helpful AI assistant.", description="System prompt")
     temperature: float = Field(0.7, ge=0.0, le=2.0, description="Sampling temperature")
     top_p: float = Field(0.9, ge=0.0, le=1.0, description="Top-p sampling")
-    top_k: int = Field(40, ge=1, le=100, description="Top-k sampling")
+    top_k: int = Field(40, ge=-1, le=100, description="Top-k sampling")
     max_new_tokens: int = Field(512, ge=1, le=4096, description="Maximum tokens to generate")
     repetition_penalty: float = Field(1.1, ge=1.0, le=2.0, description="Repetition penalty")
     image_base64: Optional[str] = Field(None, description="Base64 encoded image for vision models")
@@ -128,7 +128,7 @@ class ChatCompletionRequest(BaseModel):
     max_tokens: Optional[int] = Field(512, ge=1, le=4096, description="Maximum tokens to generate")
 
     # ── Unsloth extensions (ignored by standard OpenAI clients) ──
-    top_k: int = Field(40, ge=1, le=100, description="[x-unsloth] Top-k sampling")
+    top_k: int = Field(40, ge=-1, le=100, description="[x-unsloth] Top-k sampling")
     min_p: float = Field(0.0, ge=0.0, le=1.0, description="[x-unsloth] Min-p sampling threshold")
     repetition_penalty: float = Field(1.1, ge=1.0, le=2.0, description="[x-unsloth] Repetition penalty")
     image_base64: Optional[str] = Field(None, description="[x-unsloth] Base64-encoded image for vision models")
diff --git a/studio/frontend/src/features/chat/chat-settings-sheet.tsx b/studio/frontend/src/features/chat/chat-settings-sheet.tsx
index 900a82a652..5a72e085ff 100644
--- a/studio/frontend/src/features/chat/chat-settings-sheet.tsx
+++ b/studio/frontend/src/features/chat/chat-settings-sheet.tsx
@@ -295,7 +295,7 @@ export function ChatSettingsPanel({
               <ParamSlider
                 label="Top K"
                 value={params.topK}
-                min={0}
+                min={-1}
                 max={100}
                 step={1}
                 onChange={set("topK")}