From f0538efb99a4e84f8d26c21da8a10290d987e953 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Wed, 24 Apr 2024 00:31:28 -0700
Subject: [PATCH] Remove obsolete --tensorcores references

---
 modules/ui.py            | 1 -
 modules/ui_model_menu.py | 1 -
 2 files changed, 2 deletions(-)

diff --git a/modules/ui.py b/modules/ui.py
index a84378b1..a7c3b0f4 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -97,7 +97,6 @@ def list_model_elements():
         'logits_all',
         'no_offload_kqv',
         'row_split',
-        'tensorcores',
         'streaming_llm',
         'attention_sink_size',
         'hqq_backend',
diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py
index 7f7a3ab8..5c4b2f89 100644
--- a/modules/ui_model_menu.py
+++ b/modules/ui_model_menu.py
@@ -119,7 +119,6 @@ def create_ui():
                             shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
                             shared.gradio['use_flash_attention_2'] = gr.Checkbox(label="use_flash_attention_2", value=shared.args.use_flash_attention_2, info='Set use_flash_attention_2=True while loading the model.')
                             shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices)
-                            shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards.')
                             shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming_llm", value=shared.args.streaming_llm, info='(experimental) Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
                             shared.gradio['attention_sink_size'] = gr.Number(label="attention_sink_size", value=shared.args.attention_sink_size, precision=0, info='StreamingLLM: number of sink tokens. Only used if the trimmed prompt doesn\'t share a prefix with the old prompt.')
                             shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu, info='llama.cpp: Use llama-cpp-python compiled without GPU acceleration. Transformers: use PyTorch in CPU mode.')