mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-25 09:09:07 -04:00
87d5734c33
The first #10485 fix (#10494) made the Blackwell physical-batch boost per-device/context-aware, which neutralized the big compute-buffer OOM, but the reporter's 2x16 GiB consumer Blackwell still OOM'd. Tracing the post-fix log: the model now loads its weights, builds the main context and warms up fine, and dies only on the *last* allocation — the MTP draft context's 800 MiB KV cache on the tighter device. #10411 changed only two defaults: the physical batch (now gated) and a VRAM-scaled parallel-slot count. The KV cache is unified (n_ctx_seq == full context proves slots share the budget, so parallel doesn't multiply KV), but n_seq_max=4 still adds per-slot compute-graph / context-checkpoint / output scratch. On a device packed ~99% by a 27B model spanning both cards, that overhead is the few-hundred-MiB straw — which is why reverting #10411 (and only #10411) restores a working load. Gate the parallel-slot default on the same per-device headroom predicate as the batch boost: when a large context already fills a single card (largeContextForDevice), keep n_parallel=1. A user running one big-context model that barely fits across two consumer GPUs is not serving four concurrent tenants. Small contexts and large unified-memory devices (GB10) keep full concurrency. Applied on both the single-host path and the distributed router. Also make the auto-tuning visible and reversible (the debugging here needed DEBUG logs and a git bisect): - Log the effective performance-relevant runtime options at INFO once per model load ("effective runtime tuning …": context, n_batch, n_gpu_layers, parallel, flash_attention, f16) so an admin can see what will run and pin or override any value in the model YAML. - LOCALAI_DISABLE_HARDWARE_DEFAULTS=true skips the hardware auto-tuning entirely (mirrors LOCALAI_DISABLE_GUESSING) for stock llama.cpp behavior. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:opus-4.8 [Claude Code]
20 lines
625 B
Go
20 lines
625 B
Go
package model
|
|
|
|
import (
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
)
|
|
|
|
var _ = Describe("parallelSlotsFromOptions", func() {
|
|
It("reads the parallel slot count from the backend options", func() {
|
|
Expect(parallelSlotsFromOptions([]string{"use_jinja:true", "parallel:4"})).To(Equal("4"))
|
|
})
|
|
It("accepts the n_parallel alias", func() {
|
|
Expect(parallelSlotsFromOptions([]string{"n_parallel:8"})).To(Equal("8"))
|
|
})
|
|
It("defaults to a single slot when unset", func() {
|
|
Expect(parallelSlotsFromOptions([]string{"use_jinja:true"})).To(Equal("1"))
|
|
Expect(parallelSlotsFromOptions(nil)).To(Equal("1"))
|
|
})
|
|
})
|