llmgw ctl model gpus MODEL N [--profile P] [--in-place],
POST /api/v1/models/{name}/gpus and the console's GPUs…: how many cards of
one node each replica uses. Tensor parallel for vLLM, SGLang and
TensorRT-LLM, held to the model's KV heads (modelplan.SplitsHeads, now one
rule for the planner and this); the layers split for llama.cpp, its old
--tensor-split dropped. Refused for a count no node has, for cards that
would not hold the weights and the context, and for engines on one card.
The replicas start again beside the old ones; with no room beside them the
command says so, and --in-place stops each first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
51aeadae3e
commit
e1cff0d4e3
16 files changed
+753
-13
No files matched your search
@@ -155,10 +155,7 @@ func fitsOn(m Model, h Hardware, d Demand, p Precision, context int) []Fit {
|
||||
if nodes > 1 && h.Fabric == "" {
|
||||
continue
|
||||
}
|
||||
// The KV heads are split among the cards, or past their number each
|
||||
// card holds a copy of one: the width divides them or they divide
|
||||
// it. A model with 8 KV heads splits 2, 4, 8 or 16 ways, not 12.
|
||||
if m.KVHeads > 0 && m.KVHeads%width != 0 && width%m.KVHeads != 0 {
|
||||
if !SplitsHeads(m.KVHeads, width) {
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user