Logo
Explore Help
Register Sign In
biondizzle/vllm
1
0
Fork 0
You've already forked vllm
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
ec090c2429d179309641cba9e7793eab34e19f8d
vllm/vllm/tokenizers
History
Nick Hill a96197f564 [Perf] Simplify DeepseekV32 tokenizer, ensure fast detokenization used (#33855)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-02-08 07:16:34 +00:00
..
__init__.py
[Chore][1/2] Drop v0.14 deprecations (#31285)
2025-12-24 09:54:01 -08:00
deepseek_v32_encoding.py
Remove deprecated reasoning_content message field (#33402)
2026-01-30 11:48:15 +00:00
deepseek_v32.py
[Perf] Simplify DeepseekV32 tokenizer, ensure fast detokenization used (#33855)
2026-02-08 07:16:34 +00:00
detokenizer_utils.py
[Bugfix] Fix DeepSeek v3.2 tokenizer outputting None issue (#33832)
2026-02-05 23:50:49 +00:00
grok2.py
feat(frontend): early-fail tokenization guard for user requests (#31366)
2026-02-05 19:38:02 -08:00
hf.py
feat(frontend): early-fail tokenization guard for user requests (#31366)
2026-02-05 19:38:02 -08:00
mistral.py
feat(frontend): early-fail tokenization guard for user requests (#31366)
2026-02-05 19:38:02 -08:00
protocol.py
feat(frontend): early-fail tokenization guard for user requests (#31366)
2026-02-05 19:38:02 -08:00
registry.py
Improve Mistral format checks. (#33253)
2026-01-30 06:23:33 -08:00
Powered by Gitea Version: 1.25.2 Page: 154ms Template: 2ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API