- 10 Jan, 2024 4 commits
-
-
Daniel Hiltgen authored
When there are multiple management libraries installed on a system not every one will be compatible with the current driver. This change improves our management library algorithm to build up a set of discovered libraries based on glob patterns, and then try all of them until we're able to load one without error.
-
Daniel Hiltgen authored
This can help speed up incremental builds when you're only testing one archicture, like amd64. E.g. BUILD_ARCH=amd64 ./scripts/build_linux.sh && scp ./dist/ollama-linux-amd64 test-system:
-
Jeffrey Morgan authored
update submodule to commit `1fc2f265ff9377a37fd2c61eae9cd813a3491bea` until its main branch is fixed
-
Jeffrey Morgan authored
* update submodule to `6efb8eb30e7025b168f3fda3ff83b9b386428ad6` * unblock condition variable in `update_slots` when closing server
-
- 09 Jan, 2024 18 commits
-
-
Jeffrey Morgan authored
-
Robin Glauser authored
Fixed assistant in the example response.
-
Jeffrey Morgan authored
-
Daniel Hiltgen authored
Set corret CUDA minimum compute capability version
-
Daniel Hiltgen authored
If you attempt to run the current CUDA build on compute capability 5.2 cards, you'll hit the following failure: cuBLAS error 15 at ggml-cuda.cu:7956: the requested functionality is not supported
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Michael Yang authored
fix: set template without triple quotes
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
- 08 Jan, 2024 4 commits
-
-
Michael Yang authored
fix(cmd): history in alt prompt
-
Jeffrey Morgan authored
* select layers based on estimated model memory usage * always account for scratch vram * dont load +1 layers * better estmation for graph alloc * Update gpu/gpu_darwin.go Co-authored-by:
Bruce MacDonald <brucewmacdonald@gmail.com> * Update llm/llm.go Co-authored-by:
Bruce MacDonald <brucewmacdonald@gmail.com> * Update llm/llm.go * add overhead for cuda memory * Update llm/llm.go Co-authored-by:
Bruce MacDonald <brucewmacdonald@gmail.com> * fix build error on linux * address comments --------- Co-authored-by:
Bruce MacDonald <brucewmacdonald@gmail.com>
-
Bruce MacDonald authored
-
Bruce MacDonald authored
-
- 07 Jan, 2024 6 commits
-
-
Daniel Hiltgen authored
Detect very old CUDA GPUs and fall back to CPU
-
Daniel Hiltgen authored
Accept windows paths for image processing
-
Jeffrey Morgan authored
-
Jeffrey Morgan authored
-
Daniel Hiltgen authored
If we try to load the CUDA library on an old GPU, it panics and crashes the server. This checks the compute capability before we load the library so we can gracefully fall back to CPU mode.
-
Guilherme Baptista authored
-
- 06 Jan, 2024 5 commits
-
-
Daniel Hiltgen authored
This enhances our regex to support windows style paths. The regex will match invalid path specifications, but we'll still validate file existence and filter out mismatches
-
Daniel Hiltgen authored
Add windows native build instructions
-
Jeffrey Morgan authored
-
Michael Yang authored
Merge pull request #1797 from sublimator/nd-allow-extension-origins-still-needs-explicit-listing-2024-01-05 fix: allow extension origins (still needs explicit listing), fixes #1686
-
Michael Yang authored
-
- 05 Jan, 2024 3 commits
-
-
Michael Yang authored
-
Bruce MacDonald authored
-
Patrick Devine authored
-