oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 22:27:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ExLlamaV3: Enable the --enable-tp option, add a --tp-backend option

Browse source
This commit is contained in:
oobabooga 2025-08-17 13:19:11 -07:00
parent d771ca4a13
commit dbabe67e77
5 changed files with 16 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/ui_model_menu.py
View file

@ -46,6 +46,8 @@ def create_ui():
shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
shared.gradio['attn_implementation'] = gr.Dropdown(label="attn-implementation", choices=['sdpa', 'eager', 'flash_attention_2'], value=shared.args.attn_implementation, info='Attention implementation.')
shared.gradio['cache_type'] = gr.Dropdown(label="cache-type", choices=['fp16', 'q8_0', 'q4_0', 'fp8', 'q8', 'q7', 'q6', 'q5', 'q4', 'q3', 'q2'], value=shared.args.cache_type, allow_custom_value=True, info='Valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4; ExLlamaV3 - fp16, q2 to q8. For ExLlamaV3, you can type custom combinations for separate k/v bits (e.g. q4_q8).')
shared.gradio['tp_backend'] = gr.Dropdown(label="tp-backend", choices=['native', 'nccl'], value=shared.args.tp_backend, info='The backend for tensor parallelism.')
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.')
@ -54,7 +56,7 @@ def create_ui():
shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit)
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant, info='Used by load-in-4bit.')
shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.')
shared.gradio['enable_tp'] = gr.Checkbox(label="enable_tp", value=shared.args.enable_tp, info='Enable Tensor Parallelism (TP).')
shared.gradio['enable_tp'] = gr.Checkbox(label="enable_tp", value=shared.args.enable_tp, info='Enable tensor parallelism (TP).')
shared.gradio['cpp_runner'] = gr.Checkbox(label="cpp-runner", value=shared.args.cpp_runner, info='Enable inference with ModelRunnerCpp, which is faster than the default ModelRunner.')
shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Set trust_remote_code=True while loading the tokenizer/model. To enable this option, start the web UI with the --trust-remote-code flag.', interactive=shared.args.trust_remote_code)
shared.gradio['tensorrt_llm_info'] = gr.Markdown('* TensorRT-LLM has to be installed manually in a separate Python 3.10 environment at the moment. For a guide, consult the description of [this PR](https://github.com/oobabooga/text-generation-webui/pull/5715). \n\n* `ctx_size` is only used when `cpp-runner` is checked.\n\n* `cpp_runner` does not support streaming at the moment.')