"awq/models/aquila.py" did not exist on "bd56c301e15bfa80fb8d8d6124528f92ba528696"
- 23 May, 2024 1 commit
-
-
Daniel Hiltgen authored
This doesn't expose a UX yet, but wires the initial server portion of progress reporting during load
-
- 16 May, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 06 May, 2024 1 commit
-
-
Jeffrey Morgan authored
* fix llava models not working after first request * individual requests only for llava models
-
- 26 Apr, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 25 Apr, 2024 1 commit
-
-
jmorganca authored
-
- 02 Apr, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 23 Mar, 2024 1 commit
-
-
Daniel Hiltgen authored
The release just before ggml-cuda.cu refactoring
-
- 14 Mar, 2024 1 commit
-
-
Michael Yang authored
-
- 13 Mar, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 11 Mar, 2024 2 commits
-
-
Bruce MacDonald authored
-
Jeffrey Morgan authored
-
- 10 Mar, 2024 2 commits
-
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
- 09 Mar, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 08 Mar, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 01 Mar, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 20 Feb, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 19 Feb, 2024 1 commit
-
-
Daniel Hiltgen authored
This should resolve the problem where we don't fully unload from the GPU when we go idle.
-
- 12 Feb, 2024 1 commit
-
-
Jeffrey Morgan authored
-
- 06 Feb, 2024 1 commit
-
-
Daniel Hiltgen authored
-
- 31 Jan, 2024 1 commit
-
-
Daniel Hiltgen authored
This requires an upstream change to support graceful termination, carried as a patch.
-
- 25 Jan, 2024 1 commit
-
-
Jeffrey Morgan authored
* Fix clearing kv cache between requests with the same prompt * fix powershell script
-
