GitLab

During testing, we're seeing some models take over 3 minutes.

This commit introduces a more friendly way to build Ollama dependencies
and the binary without abusing `go generate` and removing the
unnecessary extra steps it brings with it.

This script also provides nicer feedback to the user about what is
happening during the build process.

At the end, it prints a helpful message to the user about what to do
next (e.g. run the new local Ollama).

cgo quantize

ci: use go-version-file

RAGFlow now supports integration with Ollama.

update generate scripts with new `LLAMA_CUDA` variable, set `HIP_PLATFORM` to avoid compiler errors (#3528)

Fixes gh-3514
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>

add command-r graph estimate

Add test case for context exhaustion

fix dll compress in windows building

Fail fast if mingw missing on windows

Confirmed this fails on 0.1.30 with known regression
but passes on main

CI missing archive

CI subprocess path fix

Fix CI release glitches

The subprocess change moved the build directory
arm64 builds weren't setting cross-compilation flags when building on x86

update graph size estimate

default head_kv to 1

This also moves the checkServerHeartbeat call out of the "RunE" Cobra
stuff (that's the only word I have for that) to on-site where it's after
the check for OLLAMA_MODELS, which allows the helpful error message to
be printed before the server heartbeat check. This also arguably makes
the code more readable without the magic/superfluous "pre" function
caller.

Fix numgpu opt miscomparison

Co-authored-by: Pier Francesco Contino <pfcontino@gmail.com>

fix metal gpu