mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-12 22:33:54 -04:00
localai-org-maint-botandEttore Di Giacinto
561d623976
* docs: design EXL3 gallery entries Define the pinned Qwen3.8 and DeepSeek V4 Flash entries before changing the gallery. Assisted-by: Codex:gpt-5 [web] * feat(gallery): add EXL3 vllm.cpp models Add pinned Qwen3.8 and DeepSeek V4 Flash configurations. Bind the staged DFlash companion path so vllm.cpp opens LocalAI's managed snapshot. Assisted-by: Codex:gpt-5 --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
39 lines
1.0 KiB
Go
39 lines
1.0 KiB
Go
package main
|
|
|
|
import (
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
)
|
|
|
|
var _ = Describe("managed DFlash companion options", func() {
|
|
It("replaces only the draft model in an existing speculative configuration", func() {
|
|
managedPath := ".artifacts/huggingface/0123456789abcdef/snapshot"
|
|
lo := parseOptions(&pb.ModelOptions{
|
|
Options: []string{"draft_model:" + managedPath},
|
|
EngineArgs: `{
|
|
"speculative_config": {
|
|
"method": "dflash",
|
|
"model": "Mia-AiLab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw",
|
|
"num_speculative_tokens": 7
|
|
}
|
|
}`,
|
|
})
|
|
|
|
Expect(lo.speculativeConfig).To(MatchJSON(`{
|
|
"method": "dflash",
|
|
"model": ".artifacts/huggingface/0123456789abcdef/snapshot",
|
|
"num_speculative_tokens": 7
|
|
}`))
|
|
})
|
|
|
|
It("ignores a draft companion when speculative decoding is not configured", func() {
|
|
lo := parseOptions(&pb.ModelOptions{
|
|
Options: []string{"draft_model:.artifacts/huggingface/0123456789abcdef/snapshot"},
|
|
})
|
|
|
|
Expect(lo.speculativeConfig).To(BeEmpty())
|
|
})
|
|
})
|