convert.py : add python logging instead of print() (#6511)

* convert.py: add python logging instead of print()

* convert.py: verbose flag takes priority over dump flag log suppression

* convert.py: named instance logging

* convert.py: use explicit logger id string

* convert.py: convert extra print() to named logger

* convert.py: sys.stderr.write --> logger.error

* *.py: Convert all python scripts to use logging module

* requirements.txt: remove extra line

* flake8: update flake8 ignore and exclude to match ci settings

* gh-actions: add flake8-no-print to flake8 lint step

* pre-commit: add flake8-no-print to flake8 and also update pre-commit version

* convert-hf-to-gguf.py: print() to logger conversion

* *.py: logging basiconfig refactor to use conditional expression

* *.py: removed commented out logging

* fixup! *.py: logging basiconfig refactor to use conditional expression

* constant.py: logger.error then exit should be a raise exception instead

* *.py: Convert logger error and sys.exit() into a raise exception (for atypical error)

* gguf-convert-endian.py: refactor convert_byteorder() to use tqdm progressbar

* verify-checksum-model.py: This is the result of the program, it should be printed to stdout.

* compare-llama-bench.py: add blank line for readability during missing repo response

* reader.py: read_gguf_file() use print() over logging

* convert.py: warning goes to stderr and won't hurt the dump output

* gguf-dump.py: dump_metadata() should print to stdout

* convert-hf-to-gguf.py: print --> logger.debug or ValueError()

* verify-checksum-models.py: use print() for printing table

* *.py: refactor logging.basicConfig()

* gguf-py/gguf/*.py: use __name__ as logger name

Since they will be imported and not run directly.

* python-lint.yml: use .flake8 file instead

* constants.py: logger no longer required

* convert-hf-to-gguf.py: add additional logging

* convert-hf-to-gguf.py: print() --> logger

* *.py: fix flake8 warnings

* revert changes to convert-hf-to-gguf.py for get_name()

* convert-hf-to-gguf-update.py: use triple quoted f-string instead

* *.py: accidentally corrected the wrong line

* *.py: add compilade warning suggestions and style fixes
This commit is contained in:
Brian 2024-05-04 05:36:41 +10:00 committed by GitHub
parent 433def286e
commit a2ac89d6ef
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 536 additions and 482 deletions

View file

@ -1,5 +1,6 @@
#!/usr/bin/env python3
import logging
import argparse
import heapq
import sys
@ -11,9 +12,11 @@ try:
import git
from tabulate import tabulate
except ImportError as e:
print("ERROR: the following Python libraries are required: GitPython, tabulate.")
print("the following Python libraries are required: GitPython, tabulate.") # noqa: NP100
raise e
logger = logging.getLogger("compare-llama-bench")
# Properties by which to differentiate results per commit:
KEY_PROPERTIES = [
"cpu_info", "gpu_info", "n_gpu_layers", "main_gpu", "cuda", "opencl", "metal", "gpu_blas",
@ -94,8 +97,7 @@ parser.add_argument("-s", "--show", help=help_s)
known_args, unknown_args = parser.parse_known_args()
if unknown_args:
print(f"ERROR: Received unknown args: {unknown_args}.")
print()
logger.error(f"Received unknown args: {unknown_args}.")
parser.print_help()
sys.exit(1)
@ -108,8 +110,7 @@ if input_file is None:
input_file = sqlite_files[0]
if input_file is None:
print("ERROR: Cannot find a suitable input file, please provide one.")
print()
logger.error("Cannot find a suitable input file, please provide one.")
parser.print_help()
sys.exit(1)
@ -194,23 +195,19 @@ if known_args.baseline is not None:
hexsha8_baseline = get_commit_hexsha8(known_args.baseline)
name_baseline = known_args.baseline
if hexsha8_baseline is None:
print(f"ERROR: cannot find data for baseline={known_args.baseline}.")
logger.error(f"cannot find data for baseline={known_args.baseline}.")
sys.exit(1)
# Otherwise, search for the most recent parent of master for which there is data:
elif repo is not None:
hexsha8_baseline = find_parent_in_data(repo.heads.master.commit)
if hexsha8_baseline is None:
print("ERROR: No baseline was provided and did not find data for any master branch commits.")
print()
logger.error("No baseline was provided and did not find data for any master branch commits.")
parser.print_help()
sys.exit(1)
else:
print(
"ERROR: No baseline was provided and the current working directory "
"is not part of a git repository from which a baseline could be inferred."
)
print()
logger.error("No baseline was provided and the current working directory "
"is not part of a git repository from which a baseline could be inferred.")
parser.print_help()
sys.exit(1)
@ -227,7 +224,7 @@ if known_args.compare is not None:
hexsha8_compare = get_commit_hexsha8(known_args.compare)
name_compare = known_args.compare
if hexsha8_compare is None:
print(f"ERROR: cannot find data for compare={known_args.compare}.")
logger.error(f"cannot find data for compare={known_args.compare}.")
sys.exit(1)
# Otherwise, search for the commit for llama-bench was most recently run
# and that is not a parent of master:
@ -241,16 +238,12 @@ elif repo is not None:
break
if hexsha8_compare is None:
print("ERROR: No compare target was provided and did not find data for any non-master commits.")
print()
logger.error("No compare target was provided and did not find data for any non-master commits.")
parser.print_help()
sys.exit(1)
else:
print(
"ERROR: No compare target was provided and the current working directory "
"is not part of a git repository from which a compare target could be inferred."
)
print()
logger.error("No compare target was provided and the current working directory "
"is not part of a git repository from which a compare target could be inferred.\n")
parser.print_help()
sys.exit(1)
@ -284,8 +277,7 @@ if known_args.show is not None:
if prop not in KEY_PROPERTIES[:-2]: # Last two values are n_prompt, n_gen.
unknown_cols.append(prop)
if unknown_cols:
print(f"ERROR: Unknown values for --show: {', '.join(unknown_cols)}")
print()
logger.error(f"Unknown values for --show: {', '.join(unknown_cols)}")
parser.print_usage()
sys.exit(1)
rows_show = get_rows(show)
@ -369,7 +361,7 @@ if "gpu_info" in show:
headers = [PRETTY_NAMES[p] for p in show]
headers += ["Test", f"t/s {name_baseline}", f"t/s {name_compare}", "Speedup"]
print(tabulate(
logger.info(tabulate(
table,
headers=headers,
floatfmt=".2f",

View file

@ -1,5 +1,6 @@
#!/usr/bin/env python3
import logging
import argparse
import os
import subprocess
@ -7,6 +8,8 @@ import sys
import yaml
logger = logging.getLogger("run-with-preset")
CLI_ARGS_MAIN_PERPLEXITY = [
"batch-size", "cfg-negative-prompt", "cfg-scale", "chunks", "color", "ctx-size", "escape",
"export", "file", "frequency-penalty", "grammar", "grammar-file", "hellaswag",
@ -56,6 +59,7 @@ parser.add_argument("-bin", "--binary", help="The binary to run.")
parser.add_argument("yaml_files", nargs="*",
help="Arbitrary number of YAML files from which to read preset values. "
"If two files specify the same values the later one will be used.")
parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
known_args, unknown_args = parser.parse_known_args()
@ -63,6 +67,8 @@ if not known_args.yaml_files and not unknown_args:
parser.print_help()
sys.exit(0)
logging.basicConfig(level=logging.DEBUG if known_args.verbose else logging.INFO)
props = dict()
for yaml_file in known_args.yaml_files:
@ -85,7 +91,7 @@ elif binary.lower().endswith("llama-bench"):
elif binary.lower().endswith("server"):
cli_args = CLI_ARGS_SERVER
else:
print(f"Unknown binary: {binary}")
logger.error(f"Unknown binary: {binary}")
sys.exit(1)
command_list = [binary]
@ -121,11 +127,11 @@ for cli_arg in cli_args:
num_unused = len(props)
if num_unused > 10:
print(f"The preset file contained a total of {num_unused} unused properties.")
logger.info(f"The preset file contained a total of {num_unused} unused properties.")
elif num_unused > 0:
print("The preset file contained the following unused properties:")
logger.info("The preset file contained the following unused properties:")
for prop, value in props.items():
print(f" {prop}: {value}")
logger.info(f" {prop}: {value}")
command_list += unknown_args

View file

@ -1,8 +1,11 @@
#!/usr/bin/env python3
import logging
import os
import hashlib
logger = logging.getLogger("verify-checksum-models")
def sha256sum(file):
block_size = 16 * 1024 * 1024 # 16 MB block size
@ -27,7 +30,7 @@ hash_list_file = os.path.join(llama_path, "SHA256SUMS")
# Check if the hash list file exists
if not os.path.exists(hash_list_file):
print(f"Hash list file not found: {hash_list_file}")
logger.error(f"Hash list file not found: {hash_list_file}")
exit(1)
# Read the hash file content and split it into an array of lines
@ -46,7 +49,7 @@ for line in hash_list:
file_path = os.path.join(llama_path, filename)
# Informing user of the progress of the integrity check
print(f"Verifying the checksum of {file_path}")
logger.info(f"Verifying the checksum of {file_path}")
# Check if the file exists
if os.path.exists(file_path):
@ -73,9 +76,9 @@ for line in hash_list:
# Print column headers for results table
print("\n" + "filename".ljust(40) + "valid checksum".center(20) + "file missing".center(20))
print("-" * 80)
print("filename".ljust(40) + "valid checksum".center(20) + "file missing".center(20)) # noqa: NP100
print("-" * 80) # noqa: NP100
# Output the results as a table
for r in results:
print(f"{r['filename']:40} {r['valid checksum']:^20} {r['file missing']:^20}")
print(f"{r['filename']:40} {r['valid checksum']:^20} {r['file missing']:^20}") # noqa: NP100