Files
LocalAI/backend/go/parakeet-cpp/main.go
LocalAI [bot] 860f9d63ad feat(parakeet-cpp): dynamic batching for concurrent transcription requests (#10112)
* feat(parakeet-cpp): dynamic-batching scheduler (queue + dispatcher)

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(parakeet-cpp): dynamic batching for AudioTranscription via batched JSON C-API

Drop SingleThread; route unary transcription through the in-process batcher
which coalesces concurrent requests into one batched engine call. Streaming
stays mutually exclusive via engineMu. Adds batch_max_size / batch_max_wait_ms
options (size=1 disables; recommended on CPU).

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(parakeet-cpp): tear down dispatcher in Free; log batch config; preallocate; clarify stream lock

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(parakeet-cpp): Ginkgo batcher tests; optional batch C-API binding with per-request fallback

The batched JSON C-API symbol exists only in newer libparakeet.so (ABI >= 2);
probe it with Dlsym and register optionally so the backend still loads against
an older library, falling back to per-request transcription. Rewrites the
batcher unit tests as Ginkgo/Gomega specs (forbidigo bans t.Fatal in tests).

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(parakeet-cpp): debug-log coalesced batch size in runBatch

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(parakeet-cpp): default batch_max_size to 1 (batching opt-in)

Dynamic batching now defaults off (batch_max_size:1, one request at a
time). Raise batch_max_size to opt in: it is a large throughput win on
GPU under concurrent load, but on CPU and low-concurrency setups it only
adds latency, so off is the safer default. The startup log now states
whether batching is on or off, and the audio-to-text docs are updated to
match.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

* chore(parakeet-cpp): bump parakeet.cpp to 8a7c482 (batched decode + B=1 fast-path)

parakeet.cpp PR #1 merged the batched encoder/decode and the B=1 encoder
fast-path to master. Point PARAKEET_VERSION at that commit so the backend
builds the batched C-API (parakeet_capi_transcribe_pcm_batch_json) that the
dynamic batcher calls; the prior pin (30a3075) predated it, so only the
per-request fallback path was exercised. Verified the shared lib builds with
the backend's CMake flags and exports the batch symbol.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-06-02 14:49:02 +02:00

76 lines
2.4 KiB
Go

package main
// Started internally by LocalAI - one gRPC server per loaded model.
//
// Loads libparakeet.so via purego and registers the flat C-API entry
// points declared in parakeet_capi.h. The library name can be overridden
// with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY / VIBEVOICECPP_LIBRARY
// convention in the sibling backends); the default looks for the .so next
// to this binary.
import (
"flag"
"fmt"
"os"
"github.com/ebitengine/purego"
grpc "github.com/mudler/LocalAI/pkg/grpc"
)
var (
addr = flag.String("addr", "localhost:50051", "the address to connect to")
)
type LibFuncs struct {
FuncPtr any
Name string
}
func main() {
libName := os.Getenv("PARAKEET_LIBRARY")
if libName == "" {
libName = "libparakeet.so"
}
lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
if err != nil {
panic(fmt.Errorf("parakeet-cpp: dlopen %q: %w", libName, err))
}
// Bound 1:1 to parakeet_capi.h. The C-API returns malloc'd char*
// buffers from transcribe_*; we register those as uintptr so we get
// the raw pointer back and can call parakeet_capi_free_string on it
// (purego's string return would copy and forget the original pointer,
// leaking it on every call).
libFuncs := []LibFuncs{
{&CppAbiVersion, "parakeet_capi_abi_version"},
{&CppLoad, "parakeet_capi_load"},
{&CppFree, "parakeet_capi_free"},
{&CppTranscribePath, "parakeet_capi_transcribe_path"},
{&CppTranscribePathJSON, "parakeet_capi_transcribe_path_json"},
{&CppStreamBegin, "parakeet_capi_stream_begin"},
{&CppStreamFeed, "parakeet_capi_stream_feed"},
{&CppStreamFinalize, "parakeet_capi_stream_finalize"},
{&CppStreamFree, "parakeet_capi_stream_free"},
{&CppFreeString, "parakeet_capi_free_string"},
{&CppLastError, "parakeet_capi_last_error"},
}
for _, lf := range libFuncs {
purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
}
// The batched-JSON entry point exists only in newer libparakeet.so (ABI >= 2).
// Probe with Dlsym and register only if present, so the backend still loads
// against an older library (it falls back to per-request transcription).
if sym, err := purego.Dlsym(lib, "parakeet_capi_transcribe_pcm_batch_json"); err == nil && sym != 0 {
purego.RegisterLibFunc(&CppTranscribePcmBatchJSON, lib, "parakeet_capi_transcribe_pcm_batch_json")
}
fmt.Fprintf(os.Stderr, "[parakeet-cpp] ABI=%d\n", CppAbiVersion())
flag.Parse()
if err := grpc.StartServer(*addr, &ParakeetCpp{}); err != nil {
panic(err)
}
}