25 Commits

Author SHA1 Message Date
jmorganca
cd776e49ad llama: wip vision support for runner 2024-08-12 22:18:30 -07:00
Daniel Hiltgen
3cc7ec4429 fix dolphin-mistral 2024-08-01 14:50:36 -07:00
Daniel Hiltgen
46c5f5fd9e Runtime selection of new or old runners
This adjusts the new runners to comingle with existing runners so we can use an
env var to toggle the new runners on.
2024-08-01 09:06:01 -07:00
Daniel Hiltgen
c1384c8bcc Implement timings response in Go server
This implements the fields necessary for `run --verbose`
to generate timing information.
2024-08-01 09:05:08 -07:00
Daniel Hiltgen
d0e239b85f
Merge pull request #6110 from dhiltgen/go_server_embeds
llama: Get embeddings working
2024-08-01 07:59:35 -07:00
Daniel Hiltgen
b2f8a6120c Get embeddings working
Truncation doesn't pass, but the other embeddings tests pass
2024-07-31 17:03:05 -07:00
Daniel Hiltgen
71b287264d Fix parallel requests 2024-07-31 15:21:43 -07:00
jmorganca
2abf81885d lint 2024-07-29 15:38:52 -07:00
jmorganca
ac090b6b71 fix issues with runner 2024-07-29 15:38:51 -07:00
jmorganca
028fda3582 cleanup stop code 2024-07-29 15:38:51 -07:00
jmorganca
a796b7aeaf num predict 2024-07-29 15:38:51 -07:00
jmorganca
89cb4b8d6b basic progress 2024-07-29 15:38:51 -07:00
jmorganca
0d365e8d34 add more runner params 2024-07-29 15:38:51 -07:00
jmorganca
72ff94efe0 truncate stop properly 2024-07-29 15:38:51 -07:00
jmorganca
240d4cf0aa wip stop tokens 2024-07-29 15:38:51 -07:00
jmorganca
424627c347 embeddings 2024-07-29 15:38:51 -07:00
jmorganca
1a801fba2a remove dependency on llm 2024-07-29 15:38:51 -07:00
jmorganca
727494ea54 grammar 2024-07-29 15:38:51 -07:00
jmorganca
b39fca7088 sampling 2024-07-29 15:38:51 -07:00
jmorganca
db55b1b89d better example module, add port 2024-07-29 15:38:51 -07:00
jmorganca
1124e24aff wip 2024-07-29 15:38:51 -07:00
jmorganca
df44d119a3 add llava to runner 2024-07-29 15:38:51 -07:00
jmorganca
878eb9a19f add llava 2024-07-29 15:38:51 -07:00
jmorganca
4dd63c1fef move runner package down 2024-07-29 15:38:51 -07:00
jmorganca
82214396b5 replace static build in llm 2024-07-29 15:38:51 -07:00