This website requires JavaScript.
Explore
Help
Sign In
youngkingdom
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
0ee535b2945d042cbb1fc6e63fd3fddd94d491f2
vllm
/
tests
/
spec_decode
/
e2e
History
Cody Yu
f942efb5a3
[Dynamic Spec Decoding] Auto-disable by the running queue size (
#4592
)
...
Co-authored-by: Cade Daniel <
edacih@gmail.com
>
2024-05-08 21:44:00 +00:00
..
__init__.py
[Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (
#3951
)
2024-04-23 08:02:36 +00:00
conftest.py
[Bug fix][Core] fixup ngram not setup correctly (
#4551
)
2024-05-07 11:40:18 -07:00
test_compatibility.py
[BugFix] fix num_lookahead_slots missing in async executor (
#4165
)
2024-04-30 10:12:59 -07:00
test_logprobs.py
[Speculative decoding] Support target-model logprobs (
#4378
)
2024-05-03 15:52:01 -07:00
test_multistep_correctness.py
[Dynamic Spec Decoding] Auto-disable by the running queue size (
#4592
)
2024-05-08 21:44:00 +00:00
test_ngram_correctness.py
[Dynamic Spec Decoding] Auto-disable by the running queue size (
#4592
)
2024-05-08 21:44:00 +00:00