llama.cpp: Remove the --flash-attn flag (it's always on now)

modules/llama_cpp_server.py

@@ -318,8 +318,6 @@ class LlamaServer:
             "--no-webui",
         ]
 
-        if shared.args.flash_attn:
-            cmd.append("--flash-attn")
         if shared.args.threads > 0:
             cmd += ["--threads", str(shared.args.threads)]
         if shared.args.threads_batch > 0:

modules/loaders.py

@@ -16,7 +16,6 @@ loaders_and_params = OrderedDict({
         'streaming_llm',
         'rope_freq_base',
         'compress_pos_emb',
-        'flash_attn',
         'row_split',
         'no_kv_offload',
         'no_mmap',

modules/shared.py

@@ -73,7 +73,6 @@ group.add_argument('--quant_type', type=str, default='nf4', help='quant_type for
 
 # llama.cpp
 group = parser.add_argument_group('llama.cpp')
-group.add_argument('--flash-attn', action='store_true', help='Use flash-attention.')
 group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
 group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')
 group.add_argument('--batch-size', type=int, default=256, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
@@ -159,9 +158,6 @@ group.add_argument('--api-enable-ipv6', action='store_true', help='Enable IPv6 f
 group.add_argument('--api-disable-ipv4', action='store_true', help='Disable IPv4 for the API')
 group.add_argument('--nowebui', action='store_true', help='Do not launch the Gradio UI. Useful for launching the API in standalone mode.')
 
-# Deprecated parameters
-group = parser.add_argument_group('Deprecated')
-
 # Handle CMD_FLAGS.txt
 cmd_flags_path = Path(__file__).parent.parent / "user_data" / "CMD_FLAGS.txt"
 if cmd_flags_path.exists():

modules/ui.py

@@ -142,7 +142,6 @@ def list_model_elements():
         'num_experts_per_token',
         'load_in_8bit',
         'load_in_4bit',
-        'flash_attn',
         'attn_implementation',
         'cpu',
         'disk',

modules/ui_model_menu.py

@@ -50,7 +50,6 @@ def create_ui():
 
                         with gr.Column():
                             shared.gradio['vram_info'] = gr.HTML(value=get_initial_vram_info())
-                            shared.gradio['flash_attn'] = gr.Checkbox(label="flash-attn", value=shared.args.flash_attn, info='Use flash-attention.')
                             shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming-llm", value=shared.args.streaming_llm, info='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
                             shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
                             shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit)