tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

py : type-check all Python scripts with Pyright (#8341)

Browse Source 
* py : type-check all Python scripts with Pyright

* server-tests : use trailing slash in openai base_url

* server-tests : add more type annotations

* server-tests : strip "chat" from base_url in oai_chat_completions

* server-tests : model metadata is a dict

* ci : disable pip cache in type-check workflow

The cache is not shared between branches, and it's 250MB in size,
so it would become quite a big part of the 10GB cache limit of the repo.

* py : fix new type errors from master branch

* tests : fix test-tokenizer-random.py

Apparently, gcc applies optimisations even when pre-processing,
which confuses pycparser.

* ci : only show warnings and errors in python type-check

The "information" level otherwise has entries
from 'examples/pydantic_models_to_grammar.py',
which could be confusing for someone trying to figure out what failed,
considering that these messages can safely be ignored
even though they look like errors.
This commit is contained in:
compilade
2024-07-07 15:04:39 -04:00
committed by GitHub
parent a8db2a9ce6
commit 3fd62a6b1c
33 changed files with 297 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
scripts/gen-unicode-data.py
View File

@ -1,3 +1,5 @@
from __future__ import annotations
import array
import unicodedata
import requests
@ -133,7 +135,7 @@ table_nfd.sort()
# group ranges with same flags
ranges_flags = [(0, codepoint_flags[0])] # start, flags
ranges_flags: list[tuple[int, int]] = [(0, codepoint_flags[0])] # start, flags
for codepoint, flags in enumerate(codepoint_flags):
if flags != ranges_flags[-1][1]:
ranges_flags.append((codepoint, flags))
@ -141,11 +143,11 @@ ranges_flags.append((MAX_CODEPOINTS, 0x0000))
# group ranges with same nfd
ranges_nfd = [(0, 0, 0)] # start, last, nfd
ranges_nfd: list[tuple[int, int, int]] = [(0, 0, 0)] # start, last, nfd
for codepoint, norm in table_nfd:
start = ranges_nfd[-1][0]
if ranges_nfd[-1] != (start, codepoint - 1, norm):
ranges_nfd.append(None)
ranges_nfd.append(None) # type: ignore[arg-type] # dummy, will be replaced below
start = codepoint
ranges_nfd[-1] = (start, codepoint, norm)
@ -179,13 +181,13 @@ for codepoint in table_whitespace:
out("};\n")
out("const std::unordered_map<uint32_t, uint32_t> unicode_map_lowercase = {")
for tuple in table_lowercase:
out("{0x%06X, 0x%06X}," % tuple)
for tuple_lw in table_lowercase:
out("{0x%06X, 0x%06X}," % tuple_lw)
out("};\n")
out("const std::unordered_map<uint32_t, uint32_t> unicode_map_uppercase = {")
for tuple in table_uppercase:
out("{0x%06X, 0x%06X}," % tuple)
for tuple_up in table_uppercase:
out("{0x%06X, 0x%06X}," % tuple_up)
out("};\n")
out("const std::vector<range_nfd> unicode_ranges_nfd = { // start, last, nfd")