Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 10:35:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Make llama-cpp-python not crash immediately

Browse source
This commit is contained in:
oobabooga 2024-07-04 19:15:37 -07:00
parent f77cf159ba
commit f243b4ca9c
3 changed files with 37 additions and 73 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

52
modules/llama_cpp_python_hijack.py
View file

@ -1,3 +1,4 @@
import importlib
from typing import Sequence
from tqdm import tqdm
@ -5,20 +6,38 @@ from tqdm import tqdm
from modules import shared
from modules.cache_utils import process_llamacpp_cache
try:
import llama_cpp
except:
llama_cpp = None
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
def llama_cpp_lib():
return_lib = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
if shared.args.cpu:
try:
return_lib = importlib.import_module('llama_cpp')
except:
pass
if shared.args.tensorcores and return_lib is None:
try:
return_lib = importlib.import_module('llama_cpp_cuda_tensorcores')
except:
pass
if return_lib is None:
try:
return_lib = importlib.import_module('llama_cpp_cuda')
except:
pass
if return_lib is None and not shared.args.cpu:
try:
return_lib = importlib.import_module('llama_cpp')
except:
pass
if return_lib is not None:
monkey_patch_llama_cpp_python(return_lib)
return return_lib
def eval_with_progress(self, tokens: Sequence[int]):
@ -63,7 +82,7 @@ def eval_with_progress(self, tokens: Sequence[int]):
self.n_tokens += n_tokens
def monkey_patch_generate(lib):
def monkey_patch_llama_cpp_python(lib):
def my_generate(self, *args, **kwargs):
@ -77,11 +96,6 @@ def monkey_patch_generate(lib):
for output in self.original_generate(*args, **kwargs):
yield output
lib.Llama.eval = eval_with_progress
lib.Llama.original_generate = lib.Llama.generate
lib.Llama.generate = my_generate
for lib in [llama_cpp, llama_cpp_cuda, llama_cpp_cuda_tensorcores]:
if lib is not None:
lib.Llama.eval = eval_with_progress
monkey_patch_generate(lib)

29
modules/llamacpp_hf.py
View file

@ -7,35 +7,10 @@ from torch.nn import CrossEntropyLoss
from transformers import GenerationConfig, PretrainedConfig, PreTrainedModel
from transformers.modeling_outputs import CausalLMOutputWithPast
from modules import llama_cpp_python_hijack, shared
from modules import shared
from modules.llama_cpp_python_hijack import llama_cpp_lib
from modules.logging_colors import logger
try:
import llama_cpp
except:
llama_cpp = None
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
def llama_cpp_lib():
if shared.args.cpu and llama_cpp is not None:
return llama_cpp
elif shared.args.tensorcores and llama_cpp_cuda_tensorcores is not None:
return llama_cpp_cuda_tensorcores
elif llama_cpp_cuda is not None:
return llama_cpp_cuda
else:
return llama_cpp
class LlamacppHF(PreTrainedModel):
def __init__(self, model, path):

29
modules/llamacpp_model.py
View file

@ -4,37 +4,12 @@ from functools import partial
import numpy as np
import torch
from modules import llama_cpp_python_hijack, shared
from modules import shared
from modules.callbacks import Iteratorize
from modules.llama_cpp_python_hijack import llama_cpp_lib
from modules.logging_colors import logger
from modules.text_generation import get_max_prompt_length
try:
import llama_cpp
except:
llama_cpp = None
try:
import llama_cpp_cuda
except:
llama_cpp_cuda = None
try:
import llama_cpp_cuda_tensorcores
except:
llama_cpp_cuda_tensorcores = None
def llama_cpp_lib():
if shared.args.cpu and llama_cpp is not None:
return llama_cpp
elif shared.args.tensorcores and llama_cpp_cuda_tensorcores is not None:
return llama_cpp_cuda_tensorcores
elif llama_cpp_cuda is not None:
return llama_cpp_cuda
else:
return llama_cpp
def ban_eos_logits_processor(eos_token, input_ids, logits):
logits[eos_token] = -float('inf')