gguf-inference / handler.py

Commit History

change handler
001e799

syberWolf commited on

simplify handler
96a0103

syberWolf commited on

changes for testin
6d33a5e

syberWolf commited on

update endpoint
e126c73

syberWolf commited on

forgot comma
52afa01

syberWolf commited on

update handler
eff3ac4

syberWolf commited on

fix bug
e8628b3

syberWolf commited on

try to actually use the GPU
1e592e3

syberWolf commited on

test qwen
b47e2d8

syberWolf commited on

fix handler bug
5d540d6

syberWolf commited on

updates for phi
7e91a22

syberWolf commited on

update handler and add flash attention
f96aa72

syberWolf commited on

update device map
c676380

syberWolf commited on

push updates to handler
c1cb360

syberWolf commited on

load new phi
1aeb34c

syberWolf commited on

updates with cls
f345890

syberWolf commited on

revert some sstuff
e870084

syberWolf commited on

fix bug
ca5a36d

syberWolf commited on

updates to handler again
a60a771

syberWolf commited on

dd handler change
b3aebd1

syberWolf commited on

undo reqs and fix handler
ef898a1

syberWolf commited on

change reqs
ef4c960

syberWolf commited on

update handler
17c9dd0

syberWolf commited on

add handler
fe371ad

syberWolf commited on