This website requires JavaScript.
Explore
Help
Register
Sign In
admin
/
1Cat-vLLM
Watch
1
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
098f94de42859f8251fe920f87adb88336129c53
1Cat-vLLM
/
vllm
/
spec_decode
T
History
Sungjae Lee
and
LiuXiaoxuanPKU
0c63c34f72
[Bugfix][SpecDecode] kv corruption with bonus tokens in spec decode (
#9730
)
...
Co-authored-by: LiuXiaoxuanPKU <
lilyliupku@gmail.com
>
2024-11-06 01:45:45 +00:00
..
__init__.py
…
batch_expansion.py
…
draft_model_runner.py
[Bugfix][SpecDecode] kv corruption with bonus tokens in spec decode (
#9730
)
2024-11-06 01:45:45 +00:00
interfaces.py
…
medusa_worker.py
…
metrics.py
…
mlp_speculator_worker.py
…
mqa_scorer.py
…
multi_step_worker.py
[Bugfix][SpecDecode] kv corruption with bonus tokens in spec decode (
#9730
)
2024-11-06 01:45:45 +00:00
ngram_worker.py
[2/N] executor pass the complete config to worker/modelrunner (
#9938
)
2024-11-02 07:35:05 -07:00
proposer_worker_base.py
…
smaller_tp_proposer_worker.py
…
spec_decode_worker.py
[4.5/N] bugfix for quant config in speculative decode (
#10007
)
2024-11-04 15:11:59 -08:00
target_model_runner.py
[2/N] executor pass the complete config to worker/modelrunner (
#9938
)
2024-11-02 07:35:05 -07:00
top1_proposer.py
…
util.py
…