diff --git a/README.md b/README.md index 0e653ef3..e0784e12 100644 --- a/README.md +++ b/README.md @@ -176,24 +176,31 @@ Optionally, you can use the following command-line flags: | Flag | Description | |------------------|-------------| | `-h`, `--help` | show this help message and exit | -| `--model MODEL` | Name of the model to load by default. | -| `--lora LORA` | Name of the LoRA to apply to the model by default. | | `--notebook` | Launch the web UI in notebook mode, where the output is written to the same text box as the input. | | `--chat` | Launch the web UI in chat mode.| | `--cai-chat` | Launch the web UI in chat mode with a style similar to Character.AI's. If the file `img_bot.png` or `img_bot.jpg` exists in the same folder as server.py, this image will be used as the bot's profile picture. Similarly, `img_me.png` or `img_me.jpg` will be used as your profile picture. | +| `--model MODEL` | Name of the model to load by default. | +| `--lora LORA` | Name of the LoRA to apply to the model by default. | +| `--model-dir MODEL_DIR` | Path to directory with all the models | +| `--lora-dir LORA_DIR` | Path to directory with all the loras | +| `--no-stream` | Don't stream the text output in real time. | +| `--settings SETTINGS_FILE` | Load the default interface settings from this json file. See `settings-template.json` for an example. If you create a file called `settings.json`, this file will be loaded by default without the need to use the `--settings` flag.| +| `--extensions EXTENSIONS [EXTENSIONS ...]` | The list of extensions to load. If you want to load more than one extension, write the names separated by spaces. | +| `--verbose` | Print the prompts to the terminal. | | `--cpu` | Use the CPU to generate text.| +| `--auto-devices` | Automatically split the model across the available GPU(s) and CPU.| +| `--gpu-memory GPU_MEMORY [GPU_MEMORY ...]` | Maxmimum GPU memory in GiB to be allocated per GPU. Example: `--gpu-memory 10` for a single GPU, `--gpu-memory 10 5` for two GPUs. You can also set values in MiB like `--gpu-memory 3500MiB`. | +| `--cpu-memory CPU_MEMORY` | Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.| +| `--disk` | If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk. | +| `--disk-cache-dir DISK_CACHE_DIR` | Directory to save the disk cache to. Defaults to `cache/`. | | `--load-in-8bit` | Load the model with 8-bit precision.| +| `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. | +| `--no-cache` | Set `use_cache` to False while generating text. This reduces the VRAM usage a bit with a performance cost. | +| `--threads` | Number of threads to use in llama.cpp. | | `--wbits WBITS` | GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. | | `--model_type MODEL_TYPE` | GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. | | `--groupsize GROUPSIZE` | GPTQ: Group size. | | `--pre_layer PRE_LAYER` | GPTQ: The number of layers to preload. | -| `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. | -| `--auto-devices` | Automatically split the model across the available GPU(s) and CPU.| -| `--disk` | If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk. | -| `--disk-cache-dir DISK_CACHE_DIR` | Directory to save the disk cache to. Defaults to `cache/`. | -| `--gpu-memory GPU_MEMORY [GPU_MEMORY ...]` | Maxmimum GPU memory in GiB to be allocated per GPU. Example: `--gpu-memory 10` for a single GPU, `--gpu-memory 10 5` for two GPUs. You can also set values in MiB like `--gpu-memory 3500MiB`. | -| `--cpu-memory CPU_MEMORY` | Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.| -| `--no-cache` | Set `use_cache` to False while generating text. This reduces the VRAM usage a bit with a performance cost. | | `--flexgen` | Enable the use of FlexGen offloading. | | `--percent PERCENT [PERCENT ...]` | FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0). | | `--compress-weight` | FlexGen: Whether to compress weight (default: False).| @@ -203,12 +210,6 @@ Optionally, you can use the following command-line flags: | `--local_rank LOCAL_RANK` | DeepSpeed: Optional argument for distributed setups. | | `--rwkv-strategy RWKV_STRATEGY` | RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8". | | `--rwkv-cuda-on` | RWKV: Compile the CUDA kernel for better performance. | -| `--no-stream` | Don't stream the text output in real time. | -| `--settings SETTINGS_FILE` | Load the default interface settings from this json file. See `settings-template.json` for an example. If you create a file called `settings.json`, this file will be loaded by default without the need to use the `--settings` flag.| -| `--extensions EXTENSIONS [EXTENSIONS ...]` | The list of extensions to load. If you want to load more than one extension, write the names separated by spaces. | -| `--model-dir MODEL_DIR` | Path to directory with all the models | -| `--lora-dir LORA_DIR` | Path to directory with all the loras | -| `--verbose` | Print the prompts to the terminal. | | `--listen` | Make the web UI reachable from your local network. | | `--listen-port LISTEN_PORT` | The listening port that the server will use. | | `--share` | Create a public URL. This is useful for running the web UI on Google Colab or similar. | diff --git a/modules/llamacpp_model.py b/modules/llamacpp_model.py index 5304ab7f..4f491329 100644 --- a/modules/llamacpp_model.py +++ b/modules/llamacpp_model.py @@ -1,5 +1,8 @@ +import multiprocessing + import llamacpp +from modules import shared from modules.callbacks import Iteratorize @@ -29,6 +32,7 @@ class LlamaCppModel: def from_pretrained(self, path): params = llamacpp.InferenceParams() params.path_model = str(path) + params.n_threads = shared.args.threads or multiprocessing.cpu_count() // 2 _model = llamacpp.LlamaInference(params) diff --git a/modules/shared.py b/modules/shared.py index 6f3396a7..ff133a6d 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -68,51 +68,68 @@ def str2bool(v): raise argparse.ArgumentTypeError('Boolean value expected.') parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpFormatter(prog,max_help_position=54)) -parser.add_argument('--model', type=str, help='Name of the model to load by default.') -parser.add_argument('--lora', type=str, help='Name of the LoRA to apply to the model by default.') + +# Basic settings parser.add_argument('--notebook', action='store_true', help='Launch the web UI in notebook mode, where the output is written to the same text box as the input.') parser.add_argument('--chat', action='store_true', help='Launch the web UI in chat mode.') parser.add_argument('--cai-chat', action='store_true', help='Launch the web UI in chat mode with a style similar to Character.AI\'s. If the file img_bot.png or img_bot.jpg exists in the same folder as server.py, this image will be used as the bot\'s profile picture. Similarly, img_me.png or img_me.jpg will be used as your profile picture.') -parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text.') -parser.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision.') +parser.add_argument('--model', type=str, help='Name of the model to load by default.') +parser.add_argument('--lora', type=str, help='Name of the LoRA to apply to the model by default.') +parser.add_argument("--model-dir", type=str, default='models/', help="Path to directory with all the models") +parser.add_argument("--lora-dir", type=str, default='loras/', help="Path to directory with all the loras") +parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time.') +parser.add_argument('--settings', type=str, help='Load the default interface settings from this json file. See settings-template.json for an example. If you create a file called settings.json, this file will be loaded by default without the need to use the --settings flag.') +parser.add_argument('--extensions', type=str, nargs="+", help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.') +parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.') -parser.add_argument('--gptq-bits', type=int, default=0, help='DEPRECATED: use --wbits instead.') -parser.add_argument('--gptq-model-type', type=str, help='DEPRECATED: use --model_type instead.') -parser.add_argument('--gptq-pre-layer', type=int, default=0, help='DEPRECATED: use --pre_layer instead.') +# Accelerate/transformers +parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text.') +parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.') +parser.add_argument('--gpu-memory', type=str, nargs="+", help='Maxmimum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs.') +parser.add_argument('--cpu-memory', type=str, help='Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.') +parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.') +parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".') +parser.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision.') +parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.') +parser.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces the VRAM usage a bit at a performance cost.') + +# llama.cpp +parser.add_argument('--threads', type=int, default=0, help='Number of threads to use in llama.cpp.') + +# GPTQ parser.add_argument('--wbits', type=int, default=0, help='GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.') parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.') parser.add_argument('--groupsize', type=int, default=-1, help='GPTQ: Group size.') parser.add_argument('--pre_layer', type=int, default=0, help='GPTQ: The number of layers to preload.') +parser.add_argument('--gptq-bits', type=int, default=0, help='DEPRECATED: use --wbits instead.') +parser.add_argument('--gptq-model-type', type=str, help='DEPRECATED: use --model_type instead.') +parser.add_argument('--gptq-pre-layer', type=int, default=0, help='DEPRECATED: use --pre_layer instead.') -parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.') -parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.') -parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.') -parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".') -parser.add_argument('--gpu-memory', type=str, nargs="+", help='Maxmimum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs.') -parser.add_argument('--cpu-memory', type=str, help='Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.') -parser.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces the VRAM usage a bit at a performance cost.') +# FlexGen parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.') parser.add_argument('--percent', type=int, nargs="+", default=[0, 100, 100, 0, 100, 0], help='FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0).') parser.add_argument("--compress-weight", action="store_true", help="FlexGen: activate weight compression.") parser.add_argument("--pin-weight", type=str2bool, nargs="?", const=True, default=True, help="FlexGen: whether to pin weights (setting this to False reduces CPU memory by 20%%).") + +# DeepSpeed parser.add_argument('--deepspeed', action='store_true', help='Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.') parser.add_argument('--nvme-offload-dir', type=str, help='DeepSpeed: Directory to use for ZeRO-3 NVME offloading.') parser.add_argument('--local_rank', type=int, default=0, help='DeepSpeed: Optional argument for distributed setups.') + +# RWKV parser.add_argument('--rwkv-strategy', type=str, default=None, help='RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8".') parser.add_argument('--rwkv-cuda-on', action='store_true', help='RWKV: Compile the CUDA kernel for better performance.') -parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time.') -parser.add_argument('--settings', type=str, help='Load the default interface settings from this json file. See settings-template.json for an example. If you create a file called settings.json, this file will be loaded by default without the need to use the --settings flag.') -parser.add_argument('--extensions', type=str, nargs="+", help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.') -parser.add_argument("--model-dir", type=str, default='models/', help="Path to directory with all the models") -parser.add_argument("--lora-dir", type=str, default='loras/', help="Path to directory with all the loras") -parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.') + +# Gradio parser.add_argument('--listen', action='store_true', help='Make the web UI reachable from your local network.') parser.add_argument('--listen-port', type=int, help='The listening port that the server will use.') parser.add_argument('--share', action='store_true', help='Create a public URL. This is useful for running the web UI on Google Colab or similar.') parser.add_argument('--auto-launch', action='store_true', default=False, help='Open the web UI in the default browser upon launch.') parser.add_argument("--gradio-auth-path", type=str, help='Set the gradio authentication file path. The file should contain one or more user:password pairs in this format: "u1:p1,u2:p2,u3:p3"', default=None) + args = parser.parse_args() + # Provisional, this will be deleted later deprecated_dict = {'gptq_bits': ['wbits', 0], 'gptq_model_type': ['model_type', None], 'gptq_pre_layer': ['prelayer', 0]} for k in deprecated_dict: