mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 18:36:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

build: Make target improvements (#7499)

Browse source 
* llama: wire up builtin runner

This adds a new entrypoint into the ollama CLI to run the cgo built runner.
On Mac arm64, this will have GPU support, but on all other platforms it will
be the lowest common denominator CPU build.  After we fully transition
to the new Go runners more tech-debt can be removed and we can stop building
the "default" runner via make and rely on the builtin always.

* build: Make target improvements

Add a few new targets and help for building locally.
This also adjusts the runner lookup to favor local builds, then
runners relative to the executable, and finally payloads.

* Support customized CPU flags for runners

This implements a simplified custom CPU flags pattern for the runners.
When built without overrides, the runner name contains the vector flag
we check for (AVX) to ensure we don't try to run on unsupported systems
and crash.  If the user builds a customized set, we omit the naming
scheme and don't check for compatibility.  This avoids checking
requirements at runtime, so that logic has been removed as well.  This
can be used to build GPU runners with no vector flags, or CPU/GPU
runners with additional flags (e.g. AVX512) enabled.

* Use relative paths

If the user checks out the repo in a path that contains spaces, make gets
really confused so use relative paths for everything in-repo to avoid breakage.

* Remove payloads from main binary

* install: clean up prior libraries

This removes support for v0.3.6 and older versions (before the tar bundle)
and ensures we clean up prior libraries before extracting the bundle(s).
Without this change, runners and dependent libraries could leak when we
update and lead to subtle runtime errors.
This commit is contained in:
Daniel Hiltgen 2024-12-10 09:47:19 -08:00 • committed by GitHub
parent 63269668c0
commit 4879a234c4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
58 changed files with 877 additions and 1168 deletions
Download patch file Download diff file Expand all files Collapse all files

33
discover/types.go
View file

@ -5,6 +5,7 @@ import (
"log/slog"
"github.com/ollama/ollama/format"
"github.com/ollama/ollama/runners"
)
type memInfo struct {
@ -47,6 +48,13 @@ type GpuInfo struct { // TODO better name maybe "InferenceProcessor"?
// TODO other performance capability info to help in scheduling decisions
}
func (gpu GpuInfo) RunnerName() string {
if gpu.Variant != "" {
return gpu.Library + "_" + gpu.Variant
}
return gpu.Library
}
type CPUInfo struct {
GpuInfo
CPUs []CPU
@ -99,7 +107,7 @@ func (l GpuInfoList) ByLibrary() []GpuInfoList {
for _, info := range l {
found := false
requested := info.Library
if info.Variant != CPUCapabilityNone.String() {
if info.Variant != runners.CPUCapabilityNone.String() {
requested += "_" + info.Variant
}
for i, lib := range libs {
@ -140,29 +148,6 @@ func (a ByFreeMemory) Len() int { return len(a) }
func (a ByFreeMemory) Swap(i, j int) { a[i], a[j] = a[j], a[i] }
func (a ByFreeMemory) Less(i, j int) bool { return a[i].FreeMemory < a[j].FreeMemory }
type CPUCapability uint32
// Override at build time when building base GPU runners
var GPURunnerCPUCapability = CPUCapabilityAVX
const (
CPUCapabilityNone CPUCapability = iota
CPUCapabilityAVX
CPUCapabilityAVX2
// TODO AVX512
)
func (c CPUCapability) String() string {
switch c {
case CPUCapabilityAVX:
return "avx"
case CPUCapabilityAVX2:
return "avx2"
default:
return "no vector extensions"
}
}
type SystemInfo struct {
System CPUInfo `json:"system"`
GPUs []GpuInfo `json:"gpus"`