zinccat
diff --git a/‎llama_cpp/llama.py
Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+2Lines changed: 2 additions & 0 deletions b/‎llama_cpp/llama.py
Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+2Lines changed: 2 additions & 0 deletions
diff --git a/‎llama_cpp/server/app.py
Copy file name to clipboardExpand all lines: llama_cpp/server/app.py
+51-2Lines changed: 51 additions & 2 deletions b/‎llama_cpp/server/app.py
Copy file name to clipboardExpand all lines: llama_cpp/server/app.py
+51-2Lines changed: 51 additions & 2 deletions
@@ -1380,6 +1380,7 @@ def create_chat_completion(
         mirostat_tau: float = 5.0,
         mirostat_eta: float = 0.1,
         model: Optional[str] = None,
+        logits_processor: Optional[LogitsProcessorList] = None,
     ) -> Union[ChatCompletion, Iterator[ChatCompletionChunk]]:
         """Generate a chat completion from a list of messages.
 
@@ -1421,6 +1422,7 @@ def create_chat_completion(
             mirostat_tau=mirostat_tau,
             mirostat_eta=mirostat_eta,
             model=model,
+            logits_processor=logits_processor,
         )
         if stream:
             chunks: Iterator[CompletionChunk] = completion_or_chunks  # type: ignore
 
@@ -249,13 +249,14 @@ class CreateCompletionRequest(BaseModel):
     )
     presence_penalty: Optional[float] = presence_penalty_field
     frequency_penalty: Optional[float] = frequency_penalty_field
+    logit_bias: Optional[Dict[str, float]] = Field(None)
+    logit_bias_type: Optional[Literal["input_ids", "tokens"]] = Field(None)
 
     # ignored or currently unsupported
     model: Optional[str] = model_field
     n: Optional[int] = 1
     logprobs: Optional[int] = Field(None)
     best_of: Optional[int] = 1
-    logit_bias: Optional[Dict[str, float]] = Field(None)
     user: Optional[str] = Field(None)
 
     # llama.cpp specific parameters
@@ -274,6 +275,39 @@ class Config:
 CreateCompletionResponse = create_model_from_typeddict(llama_cpp.Completion)
 
 
+def make_logit_bias_processor(
+    llama: llama_cpp.Llama,
+    logit_bias: Dict[str, float],
+    logit_bias_type: Optional[Literal["input_ids", "tokens"]],
+):
+    if logit_bias_type is None:
+        logit_bias_type = "input_ids"
+
+    to_bias: Dict[int, float] = {}
+    if logit_bias_type == "input_ids":
+        for input_id, score in logit_bias.items():
+            input_id = int(input_id)
+            to_bias[input_id] = score
+
+    elif logit_bias_type == "tokens":
+        for token, score in logit_bias.items():
+            token = token.encode('utf-8')
+            for input_id in llama.tokenize(token, add_bos=False):
+                to_bias[input_id] = score
+
+    def logit_bias_processor(
+        input_ids: List[int],
+        scores: List[float],
+    ) -> List[float]:
+        new_scores = [None] * len(scores)
+        for input_id, score in enumerate(scores):
+            new_scores[input_id] = score + to_bias.get(input_id, 0.0)
+
+        return new_scores
+
+    return logit_bias_processor
+
+
 @router.post(
     "/v1/completions",
     response_model=CreateCompletionResponse,
@@ -291,9 +325,16 @@ async def create_completion(
         "n",
         "best_of",
         "logit_bias",
+        "logit_bias_type",
         "user",
     }
     kwargs = body.dict(exclude=exclude)
+
+    if body.logit_bias is not None:
+        kwargs['logits_processor'] = llama_cpp.LogitsProcessorList([
+            make_logit_bias_processor(llama, body.logit_bias, body.logit_bias_type),
+        ])
+
     if body.stream:
         send_chan, recv_chan = anyio.create_memory_object_stream(10)
 
@@ -372,11 +413,12 @@ class CreateChatCompletionRequest(BaseModel):
     stream: bool = stream_field
     presence_penalty: Optional[float] = presence_penalty_field
     frequency_penalty: Optional[float] = frequency_penalty_field
+    logit_bias: Optional[Dict[str, float]] = Field(None)
+    logit_bias_type: Optional[Literal["input_ids", "tokens"]] = Field(None)
 
     # ignored or currently unsupported
     model: Optional[str] = model_field
     n: Optional[int] = 1
-    logit_bias: Optional[Dict[str, float]] = Field(None)
     user: Optional[str] = Field(None)
 
     # llama.cpp specific parameters
@@ -413,9 +455,16 @@ async def create_chat_completion(
     exclude = {
         "n",
         "logit_bias",
+        "logit_bias_type",
         "user",
     }
     kwargs = body.dict(exclude=exclude)
+
+    if body.logit_bias is not None:
+        kwargs['logits_processor'] = llama_cpp.LogitsProcessorList([
+            make_logit_bias_processor(llama, body.logit_bias, body.logit_bias_type),
+        ])
+
     if body.stream:
         send_chan, recv_chan = anyio.create_memory_object_stream(10)