Logo
Explore Help
Sign In
iHore/vLLM
Watch 8
Star 0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
4c33d6732148fdaeb9780fa86fca1f87f2a93c19
vLLM/vllm/v1/sample
T
History
Woosuk Kwon 41fb013d29 [V1][Spec Decode] Always use argmax for sampling draft tokens (#16899)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-23 14:57:43 -07:00
..
ops
[V1][TPU] Enable Top K (#15489)
2025-04-17 18:18:11 +00:00
tpu
[TPU][V1] Enable Top-P (#16843)
2025-04-22 00:46:07 +00:00
__init__.py
[V1] Implement vLLM V1 [1/N] (#9289)
2024-10-22 01:24:07 -07:00
metadata.py
[V1] Support bad_words in sampler (#13376)
2025-03-08 14:50:26 -08:00
rejection_sampler.py
[V1][Spec Decode] Always use argmax for sampling draft tokens (#16899)
2025-04-23 14:57:43 -07:00
sampler.py
[Bugfix] Validate logit biases to prevent out of vocab ids crashing engine (#16529)
2025-04-12 20:19:19 +00:00
Powered by Gitea Version: 1.27.2 Page: 251ms Template: 7ms
Auto
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