Skip to content

Remove --sdp-attention, --xformers flags #5126

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
oobabooga merged 2 commits into from
Dec 31, 2023
Merged

Remove --sdp-attention, --xformers flags #5126

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a8abfb2
Remove --sdp-attention, --xformers flags
oobabooga Dec 31, 2023
0108f6e
Remove an import
oobabooga Dec 31, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,8 +231,6 @@ List of command-line flags
| `--load-in-8bit` | Load the model with 8-bit precision (using bitsandbytes). |
| `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. |
| `--no-cache` | Set `use_cache` to `False` while generating text. This reduces VRAM usage slightly, but it comes at a performance cost. |
| `--xformers` | Use xformer's memory efficient attention. This is really old and probably doesn't do anything. |
| `--sdp-attention` | Use PyTorch 2.0's SDP attention. Same as above. |
| `--trust-remote-code` | Set `trust_remote_code=True` while loading the model. Necessary for some models. |
| `--no_use_fast` | Set use_fast=False while loading the tokenizer (it's True by default). Use this if you have any problems related to use_fast. |
| `--use_flash_attention_2` | Set use_flash_attention_2=True while loading the model. |
Expand Down
171 changes: 0 additions & 171 deletions modules/llama_attn_hijack.py
View file
Open in desktop

This file was deleted.

6 changes: 1 addition & 5 deletions modules/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
)

import modules.shared as shared
from modules import RoPE, llama_attn_hijack, sampler_hijack
from modules import RoPE, sampler_hijack
from modules.logging_colors import logger
from modules.models_settings import get_model_metadata
from modules.relative_imports import RelativeImport
Expand Down Expand Up @@ -97,10 +97,6 @@ def load_model(model_name, loader=None):
else:
tokenizer = load_tokenizer(model_name, model)

# Hijack attention with xformers
if any((shared.args.xformers, shared.args.sdp_attention)):
llama_attn_hijack.hijack_llama_attention()

shared.settings.update({k: v for k, v in metadata.items() if k in shared.settings})
if loader.lower().startswith('exllama'):
shared.settings['truncation_length'] = shared.args.max_seq_len
Expand Down
2 changes: 0 additions & 2 deletions modules/shared.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,8 +98,6 @@
group.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision (using bitsandbytes).')
group.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
group.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.')
group.add_argument('--xformers', action='store_true', help='Use xformer\'s memory efficient attention. This is really old and probably doesn\'t do anything.')
group.add_argument('--sdp-attention', action='store_true', help='Use PyTorch 2.0\'s SDP attention. Same as above.')
group.add_argument('--trust-remote-code', action='store_true', help='Set trust_remote_code=True while loading the model. Necessary for some models.')
group.add_argument('--force-safetensors', action='store_true', help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.')
group.add_argument('--no_use_fast', action='store_true', help='Set use_fast=False while loading the tokenizer (it\'s True by default). Use this if you have any problems related to use_fast.')
Expand Down