This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
2fa1f8ec00cf85b15422cb4c0e8eb3632ee13ea8
vLLM
/
vllm
/
model_executor
/
layers
/
quantization
/
turboquant
T
History
Dan Alistarh
ed0622e3a8
[Attention] TurboQuant: remove redundant random signs, add prior art attribution (
#40194
)
...
Signed-off-by: Dan Alistarh <
d.alistarh@gmail.com
>
2026-04-18 14:31:59 -04:00
..
__init__.py
[Attention] TurboQuant: remove redundant random signs, add prior art attribution (
#40194
)
2026-04-18 14:31:59 -04:00
centroids.py
[Attention Backend] TurboQuant: 2-bit KV cache compression with 4x capacity (
#38479
)
2026-04-14 19:57:13 -07:00
config.py
[Attention] TurboQuant: remove redundant random signs, add prior art attribution (
#40194
)
2026-04-18 14:31:59 -04:00
quantizer.py
[Attention] TurboQuant: remove redundant random signs, add prior art attribution (
#40194
)
2026-04-18 14:31:59 -04:00