Place llama.cpp across several GPUs of a node with gpus_per_node
tp on a llama.cpp profile was a width nothing placed. gpus_per_node is now the count: placement reserves that many cards on one node and the engine splits layers across them. tp, pp and nodes are refused with what to write instead. Refs #2 (item 8). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
057be16a92
commit
cbd5521f4f
5 files changed
+99
-13
No files matched your search
@@ -381,6 +381,21 @@ func (m Model) validate() error {
|
||||
}
|
||||
continue
|
||||
}
|
||||
// llama.cpp on GPUs splits a model across one node's cards by layer,
|
||||
// and how many is gpus_per_node. Not tp: llama.cpp has no tensor
|
||||
// parallelism, and a tp it was given was a width nothing placed — the
|
||||
// replica stayed unplaced, or ran on one card while four were meant.
|
||||
if p.Engine == "llamacpp" {
|
||||
switch {
|
||||
case p.Nodes > 1:
|
||||
return fmt.Errorf("model %q profile %q: llama.cpp does not span nodes; use vllm or sglang for a %d-node replica",
|
||||
m.Name, p.Name, p.Nodes)
|
||||
case p.TP > 1 || p.PP > 1:
|
||||
return fmt.Errorf("model %q profile %q: llama.cpp splits a model across a node's GPUs by layer, not by tp or pp: "+
|
||||
"write gpus_per_node: %d and leave tp and pp out", m.Name, p.Name, max(p.TP, 1)*max(p.PP, 1))
|
||||
}
|
||||
continue
|
||||
}
|
||||
// The arithmetic has to add up, or the engine is handed a shard spec it
|
||||
// cannot satisfy and fails minutes later during model loading.
|
||||
if want := p.GPUsPerNode * p.Nodes; want != p.TP*max(p.PP, 1) {
|
||||
|
||||
@@ -321,3 +321,29 @@ func TestAProfileCannotSetWhatRunsCodeInTheEngine(t *testing.T) {
|
||||
t.Errorf("ordinary tuning refused: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestALlamaCppReplicaOnSeveralGPUsSaysHowManyAsGPUsPerNode(t *testing.T) {
|
||||
four := model("big", Profile{Name: "t4", Engine: "llamacpp", GPUClass: "t4", GPUsPerNode: 4})
|
||||
c, err := New([]Model{four})
|
||||
if err != nil {
|
||||
t.Fatalf("gpus_per_node 4 on llama.cpp: %v", err)
|
||||
}
|
||||
m, _ := c.Resolve("big")
|
||||
if pl := m.PlacementProfiles(); len(pl) != 1 || pl[0].GPUsPerNode != 4 {
|
||||
t.Errorf("placement was not asked for four GPUs: %+v", pl)
|
||||
}
|
||||
// tp is a width llama.cpp has no way to use; refused, saying what to
|
||||
// write instead.
|
||||
for _, p := range []Profile{
|
||||
{Name: "tp", Engine: "llamacpp", GPUClass: "t4", TP: 4},
|
||||
{Name: "nodes", Engine: "llamacpp", GPUClass: "t4", Nodes: 2, GPUsPerNode: 1},
|
||||
} {
|
||||
_, err := New([]Model{model("x", p)})
|
||||
if err == nil {
|
||||
t.Errorf("%s: accepted", p.Name)
|
||||
}
|
||||
if p.TP == 4 && (err == nil || !strings.Contains(err.Error(), "gpus_per_node: 4")) {
|
||||
t.Errorf("tp 4 should point at gpus_per_node: %v", err)
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user