GitLab

Recent refactoring introduced a regression for filtering cuda overlap to favor newest supported version.

the check for mla omits v3 and r1 which should not return unsupported.
instead check the tokenizer for compatibility

The causal cache can store data differently depending on what is
best for the backend. We should run tests both ways.

We currently copy data into the KV cache in contiguous buffers using
ggml_cpy(). ggml_set_rows() was introduced to allow scatter operation
so that contiguous buffers are no longer required. The direct primary
benefit of this is that we no longer need to perform defragmentation.

However, GGML recently removed an optimization for ggml_cpy() and
we picked it up in 544b6739 "ggml update to b6840 (#12791)". This
caused a roughly 40% drop in token generation performance on CUDA
due to CUDA graphs no longer being used. By switching to
ggml_set_rows(), the original optimization is no longer necessary
and CUDA performance is restored.

Fixes #13112

GGML requires tensors to be contiguous for reshape and if
this is not the case, it will assert fail. Contiguous is an
expensive operation, so it's best to do it lazily when it is
actually required rather than ahead of time when it may not
be needed.

Calling abort on windows triggers the C++ runtime to attempt a debugger
attach, which causes the crashed runners to hang instead of exit, leading
to a timeout instead of a fast failure during discovery.

cuda panics on batches larger than 1024 so skip those and fallback to
cpu

* migrate to golangci-lint v2
* copyloopvar

Void is an open source AI code editor and Cursor alternative that supports
Ollama. It's built on VS Code and allows users to connect directly to Ollama
for private LLM usage without going through a middleman backend.

Key features:
- Open source Cursor alternative
- Direct Ollama integration
- VS Code fork with full compatibility
- Agent mode and MCP support
- Works with any open source model

Fixes #12919
Signed-off-by: Samaresh Kumar Singh <ssam3003@gmail.com>

* Add mla for flash attention
* Revert to using chunks

* Add supports for cgroups cores and memory limitations

* fix compile error and add logs

* remove cpu info log

* build: optimize dockerfile context for iterating

This moves the copy of the source into the layer AFTER
doing software installs so we don't have to go through
the RPM install for cuda, etc. every time you touch a
source file.

* amd: implement linux sysfs based VRAM lookup

This adds a C++ implementation of sysfs DRM VRAM discovery
for more accurate free VRAM data on linux for AMD GPUs.

Kdeps is an AI framework for building Dockerized full-stack AI
applications declaratively and uses Ollama LLM models on the
backend

Co-authored-by: pierwill <pierwill@users.noreply.github.com>

This change adds a basic benchmarking test framework for Ollama which can
be used to determine the prefill, eval, load duration, and total duration
for running a given model or models.

Many failed GPU discovery issues recently can be traced to incorrect override settings.
This extra logging should help quickly spot these and guide users to try unsetting them first.

* use slice/chunks

* bert

* llama4

* gemma3n

* gptoss

* mistral3

* qwen3vl

* qwen25vl

* deepseek2

* remove unused ops

* slice

* chunk, chunksections