GitLab

The numa flag may be having a performance impact on multi-socket systems with GPU loads

The recent cuda variant changes uncovered a bug in ByLibrary
which failed to group by common variant for GPU types.

update faq

During rebasing, the ordering was inverted causing the cuda version
selection logic to break, with driver version being evaluated as zero
incorrectly causing a downgrade to v11.

Define changed recently and this slipped through the cracks with the old
name.

* Fix embeddings memory corruption

The patch was leading to a buffer overrun corruption.  Once removed though, parallism
in server.cpp lead to hitting an assert due to slot/seq IDs being >= token count.  To
work around this, only use slot 0 for embeddings.

* Fix embed integration test assumption

The token eval count has changed with recent llama.cpp bumps (0.3.5+)

convert: update llama conversion for llama3.1

convert gemma2

convert bert model from safetensors

fix: chmod new layer to 0o644 when creating it

We're over budget for github's maximum release artifact size with rocm + 2 cuda
versions.  This splits rocm back out as a discrete artifact, but keeps the layout so it can
be extracted into the same location as the main bundle.

Fix overlapping artifact name on CI

Cuda v12

Override numParallel in pickBestPartialFitByLibrary() only if unset.

Based on compute capability and driver version, pick
v12 or v11 cuda variants.

This adds new variants for arm64 specific to Jetson platforms

This should help speed things up a little

This adjusts linux to follow a similar model to windows with a discrete archive
(zip/tgz) to cary the primary executable, and dependent libraries. Runners are
still carried as payloads inside the main binary

Darwin retain the payload model where the go binary is fully self contained.