GitLab

With the new very large parameter models, some users are willing to wait for
a very long time for models to load.

Provide a mechanism for users to set aside an amount of VRAM on each GPU
to make room for other applications they want to start after Ollama, or workaround
memory prediction bugs

On systems with low system memory, we can hit allocation failures that are difficult to diagnose
without debug logs.  This will make it easier to spot.

/Users/au/src/ollama/llm/ext_server/server.cpp:289:9: warning: 'sprintf' is deprecated: This function is provided for compatibility reasons only. Due to security concerns inherent in the design of sprintf(3), it is highly recommended that you use snprintf(3) instead.

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

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+)

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.

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.

For simplicity, perform parallelization of embedding requests in the API handler instead of offloading this to the subprocess runner. This keeps the scheduling story simpler as it builds on existing parallel requests, similar to existing text completion functionality.

Don't allow loading models that would lead to memory exhaustion (across vram, system memory and disk paging). This check was already applied on Linux but should also be applied on Windows as well.

If the system has multiple numa nodes, enable numa support in llama.cpp
If we detect numactl in the path, use that, else use the basic "distribute" mode.

* add prompt tokens to embed response

* rm slog

* metrics

* types

* prompt n

* clean up

* reset submodule

* update tests

* test name

* list metrics