When we context shift, we delete half the context and apply RoPE
with an offset to the other half. We used to RoPE across the entire
context in a single pass with a zero offset for the deleted
section. With the change to shifting in batches, we can skip any
batches where all of the offsets would be zero. This typically
reduces the number of operations by half.
Currently, when we need to do a shift on the cache, it is one
RoPE operation on the entire size of the cache (per layer). In
some cases, this can create a compute graph that is larger than
the forward pass since the forward pass is working in batches.
Since we don't consider shifting in our memory estimates, it's
possible for this to cause a crash if we run out of memory.
By limiting the size of the RoPE calls to batch size chunks, we
ensure that the shift will never exceed the size of the forward
pass, since the forward pass will also contain a RoPE of the same
size. This does not have a sigificant impact on performance since
RoPE is a math operation that is mostly proportional to the size
of its inputs.
In theory defrag could have the same issue since it also creates a
compute graph outside of the forward pass, however, since it is
only copies, it does not require any working space.
Update README.md and CLAUDE.md to correctly reference Gemma3n model
support that was added in version 1.3.0, replacing generic "Gemma 3"
references with the specific "Gemma3n" model name.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Restructure README.md for better readability and organization
- Reduce README word count by 75% while maintaining key information
- Move detailed installation guides to docs/manual-build.md
- Add Tesla K80-specific build instructions and optimizations
- Update CLAUDE.md with new documentation structure and references
- Improve title formatting with emoji and clear tagline
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add Gemma3n model support with text generation capabilities
- Add new CUDA mean operations for improved performance
- Add macOS documentation and performance tests
- Update LLAMA patches for ROCm/CUDA compatibility
- Fix various model conversion and processing issues
- Update CI workflows and build configurations
- Add library model tests and Shakespeare test data
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Copy only the ollama binary instead of entire source directory to reduce
image size and remove unnecessary symbolic link step.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
StatusError was unreachable, the client always checked for error messages in the response body first, and the server always includes error messages with HTTP error status codes.
Reporting params.NumGPULayers can be misleading because it is the
requested number of layers, not the actual number that is loaded.
While they are often the same, there are cases where they might mismatch,
such as if the GPU backend is missing.
We don't get valid UUIDs for AMD GPUs on Windows, so the best option
is to use the ordinal IDs. This brings us in line with what we currently
do on the Ollama server - the only exception is AMD GPUs on Linux, which
falls back to using ordinal IDs. The GGML implementation has no fallback
but it doesn't appear to occur for any of the GPUs that we support.
It's also possible that there are collisions between ordinal IDs for
different libraries - however the only places where we use them are
AMD on Windows and Metal on Mac, which can never occur on the same
system.
The current scheduler algorithm of picking the paralellism based on available
VRAM complicates the upcoming dynamic layer memory allocation algorithm. This
changes the default to 1, with the intent going forward that parallelism is
explicit and will no longer be dynamically determined. Removal of the dynamic
logic will come in a follow up.
