free ggml scheduler/compute scratch memory after run

docs/environment-variables.md

@@ -81,12 +81,15 @@ its var is unset. Convention: `TRANSCRIBE_<FAMILY>_GGUF`.
 | Variable | Test(s) |
 | --- | --- |
 | `TRANSCRIBE_PARAKEET_GGUF` | `parakeet_real_smoke`, `decoder_smoke` |
-| `TRANSCRIBE_PARAKEET_UNIFIED_GGUF` | `parakeet_buffered_stream_eos_smoke` |
+| `TRANSCRIBE_PARAKEET_UNIFIED_GGUF` | `parakeet_buffered_stream_eos_smoke`, `stream_offline_interleave_smoke` |
+| `TRANSCRIBE_GIGAAM_GGUF` | `gigaam_workspace_release_smoke` |
+| `TRANSCRIBE_MULTITALKER_BUNDLE_GGUF` | `parakeet_multitalker_e2e_smoke` |
+| `TRANSCRIBE_SORTFORMER_GGUF` | `sortformer_stream_ext_unit` |
 | `TRANSCRIBE_COHERE_GGUF` | `cohere_real_smoke`, `cohere_e2e_smoke` |
 | `TRANSCRIBE_WHISPER_GGUF` | `whisper_e2e_smoke`, `whisper_tokenize_parity` |
 | `TRANSCRIBE_QWEN3_ASR_GGUF` (+ `_0_6B_GGUF` / `_1_7B_GGUF`) | qwen3_asr smokes / parity |
-| `TRANSCRIBE_MOONSHINE_STREAMING_TINY_GGUF` | moonshine_streaming smokes |
-| `TRANSCRIBE_VOXTRAL_REALTIME_GGUF` | `voxtral_realtime_real_smoke` |
+| `TRANSCRIBE_MOONSHINE_STREAMING_TINY_GGUF` | moonshine_streaming smokes, `stream_offline_interleave_smoke` |
+| `TRANSCRIBE_VOXTRAL_REALTIME_GGUF` | `voxtral_realtime_real_smoke`, `stream_offline_interleave_smoke` |
 | `TRANSCRIBE_WHISPER_BIN_*` | whisper.cpp `.bin` parser/e2e fixtures |
 
 Other test/tooling vars:

src/arch/canary/canary.h

@@ -123,9 +123,7 @@ struct CanaryModel final : public transcribe_model {
 };
 
 struct CanarySession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-    ggml_tensor *        encoder_out = nullptr;
+    ggml_tensor * encoder_out = nullptr;
 
     CanaryKvCache kv_cache;
 
@@ -142,6 +140,7 @@ struct CanarySession final : public transcribe_session {
 
     CanarySession() = default;
     ~CanarySession() override;
+    void on_scratch_released() noexcept override;
 };
 
 }  // namespace transcribe::canary

src/arch/canary/model.cpp

@@ -45,14 +45,10 @@ static_assert(std::is_base_of_v<transcribe_session, CanarySession>);
 
 CanarySession::~CanarySession() {
     kv_cache.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
+}
+
+// Base release_scratch has freed sched/compute_ctx; drop what pointed into them.
+void CanarySession::on_scratch_released() noexcept {
     encoder_out = nullptr;
 }
 

src/arch/canary_qwen/canary_qwen.h

@@ -95,9 +95,6 @@ struct CanaryQwenModel final : public transcribe_model {
 };
 
 struct CanaryQwenSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     transcribe::causal_lm::KvCache kv_cache;
 
     // Batched KV cache for offline transcribe_run_batch (n_batch slabs).

src/arch/canary_qwen/model.cpp

@@ -60,14 +60,6 @@ static_assert(std::is_base_of_v<transcribe_session, CanaryQwenSession>);
 CanaryQwenSession::~CanaryQwenSession() {
     kv_cache.free();
     kv_cache_batch.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
 }
 
 CanaryQwenModel::~CanaryQwenModel() {

src/arch/cohere/cohere.h

@@ -153,9 +153,7 @@ struct CohereModel final : public transcribe_model {
 };
 
 struct CohereSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-    ggml_tensor *        encoder_out = nullptr;
+    ggml_tensor * encoder_out = nullptr;
 
     // KV cache for the decoder.
     CohereKvCache kv_cache;
@@ -174,6 +172,7 @@ struct CohereSession final : public transcribe_session {
 
     CohereSession() = default;
     ~CohereSession() override;
+    void on_scratch_released() noexcept override;
 };
 
 }  // namespace transcribe::cohere

src/arch/cohere/model.cpp

@@ -48,14 +48,10 @@ static_assert(std::is_base_of_v<transcribe_session, CohereSession>);
 
 CohereSession::~CohereSession() {
     kv_cache.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
+}
+
+// Base release_scratch has freed sched/compute_ctx; drop what pointed into them.
+void CohereSession::on_scratch_released() noexcept {
     encoder_out = nullptr;
 }
 

src/arch/funasr_nano/funasr_nano.h

@@ -74,9 +74,6 @@ struct FunAsrNanoModel final : public transcribe_model {
 };
 
 struct FunAsrNanoSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     transcribe::causal_lm::KvCache kv_cache;
 
     // Batched KV cache for offline transcribe_run_batch (n_batch slabs).

src/arch/funasr_nano/model.cpp

@@ -46,14 +46,6 @@ static_assert(std::is_base_of_v<transcribe_session, FunAsrNanoSession>);
 FunAsrNanoSession::~FunAsrNanoSession() {
     kv_cache.free();
     kv_cache_batch.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
 }
 
 FunAsrNanoModel::~FunAsrNanoModel() {

src/arch/gigaam/gigaam.h

@@ -65,9 +65,6 @@ struct GigaamModel final : public transcribe_model {
 // Concrete context. One scheduler + compute_ctx lifecycle per context,
 // mirroring parakeet.
 struct GigaamSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     ggml_tensor * encoder_out = nullptr;
 
     std::vector<float> mel_buf;
@@ -76,6 +73,7 @@ struct GigaamSession final : public transcribe_session {
 
     GigaamSession() = default;
     ~GigaamSession() override;
+    void on_scratch_released() noexcept override;
 };
 
 }  // namespace transcribe::gigaam

src/arch/gigaam/model.cpp

@@ -41,15 +41,10 @@ extern const Arch arch;
 static_assert(std::is_base_of_v<transcribe_model, GigaamModel>);
 static_assert(std::is_base_of_v<transcribe_session, GigaamSession>);
 
-GigaamSession::~GigaamSession() {
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
+GigaamSession::~GigaamSession() = default;
+
+// Base release_scratch has freed sched/compute_ctx; drop what pointed into them.
+void GigaamSession::on_scratch_released() noexcept {
     encoder_out = nullptr;
 }
 
@@ -321,7 +316,6 @@ transcribe_status run(transcribe_session * session, const float * pcm, int n_sam
     if (gm == nullptr || gm->plan.scheduler_list.empty()) {
         return TRANSCRIBE_ERR_INVALID_ARG;
     }
-
     if (gc->poll_abort()) {
         return TRANSCRIBE_ERR_ABORTED;
     }

src/arch/granite/granite.h

@@ -104,9 +104,6 @@ struct GraniteModel final : public transcribe_model {
 };
 
 struct GraniteSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     // Audio encoder output (post-projector) buffered between encode and
     // decode. Each row is one audio token in LM hidden space (2048).
     std::vector<float> mel_buf;

src/arch/granite/model.cpp

@@ -41,14 +41,6 @@ static_assert(std::is_base_of_v<transcribe_session, GraniteSession>);
 GraniteSession::~GraniteSession() {
     kv.free();
     kv_batch.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
 }
 
 GraniteModel::~GraniteModel() {

src/arch/granite_nar/granite_nar.h

@@ -56,9 +56,6 @@ struct GraniteNarModel final : public transcribe_model {
 };
 
 struct GraniteNarSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     // Encoder output buffered between encode and projector/LM.
     std::vector<float> mel_buf;
     std::vector<float> enc_cat_host;         // [T_enc, num_encoder_layers * enc_hidden]

src/arch/granite_nar/model.cpp

@@ -52,16 +52,7 @@ extern const Arch arch;
 static_assert(std::is_base_of_v<transcribe_model, GraniteNarModel>);
 static_assert(std::is_base_of_v<transcribe_session, GraniteNarSession>);
 
-GraniteNarSession::~GraniteNarSession() {
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
-}
+GraniteNarSession::~GraniteNarSession() = default;
 
 GraniteNarModel::~GraniteNarModel() {
     if (bn_fused_ctx != nullptr) {

src/arch/medasr/medasr.h

@@ -47,9 +47,6 @@ struct MedAsrModel final : public transcribe_model {
 };
 
 struct MedAsrSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     ggml_tensor * encoder_out = nullptr;
 
     std::vector<float> mel_buf;
@@ -58,6 +55,7 @@ struct MedAsrSession final : public transcribe_session {
 
     MedAsrSession() = default;
     ~MedAsrSession() override;
+    void on_scratch_released() noexcept override;
 };
 
 }  // namespace transcribe::medasr

src/arch/medasr/model.cpp

@@ -48,15 +48,10 @@ extern const Arch arch;
 static_assert(std::is_base_of_v<transcribe_model, MedAsrModel>);
 static_assert(std::is_base_of_v<transcribe_session, MedAsrSession>);
 
-MedAsrSession::~MedAsrSession() {
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
+MedAsrSession::~MedAsrSession() = default;
+
+// Base release_scratch has freed sched/compute_ctx; drop what pointed into them.
+void MedAsrSession::on_scratch_released() noexcept {
     encoder_out = nullptr;
 }
 

src/arch/moonshine/model.cpp

@@ -44,14 +44,6 @@ static_assert(std::is_base_of_v<transcribe_session, MoonshineSession>);
 
 MoonshineSession::~MoonshineSession() {
     kv_cache.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
 }
 
 MoonshineModel::~MoonshineModel() {

src/arch/moonshine/moonshine.h

@@ -123,9 +123,6 @@ struct MoonshineModel final : public transcribe_model {
 };
 
 struct MoonshineSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     // Host-side mirror of the encoder output. Required because the
     // cross-KV graph runs in a fresh compute_ctx that does not share
     // tensor handles with the encoder graph.

src/arch/moonshine_streaming/model.cpp

@@ -60,14 +60,6 @@ static_assert(std::is_base_of_v<transcribe_session, MoonshineStreamingSession>);
 
 MoonshineStreamingSession::~MoonshineStreamingSession() {
     kv_cache.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
 }
 
 MoonshineStreamingModel::~MoonshineStreamingModel() {

src/arch/moonshine_streaming/moonshine_streaming.h

@@ -119,9 +119,6 @@ struct MoonshineStreamingModel final : public transcribe_model {
 };
 
 struct MoonshineStreamingSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     // Host-side mirror of the post-adapter encoder hidden. The adapter
     // pos_emb add (and proj when present) is applied once per session;
     // this host buffer feeds the cross_kv precompute graph.

src/arch/moss/model.cpp

@@ -98,14 +98,6 @@ static_assert(std::is_base_of_v<transcribe_session, MossSession>);
 MossSession::~MossSession() {
     kv_cache.free();
     kv_cache_batch.free();
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
 }
 
 MossModel::~MossModel() {

src/arch/moss/moss.h

@@ -81,9 +81,6 @@ struct MossModel final : public transcribe_model {
 };
 
 struct MossSession final : public transcribe_session {
-    ggml_context *       compute_ctx = nullptr;
-    ggml_backend_sched_t sched       = nullptr;
-
     transcribe::causal_lm::KvCache kv_cache;
 
     // Batched KV cache for offline transcribe_run_batch (n_batch slabs).

src/arch/parakeet/model.cpp

@@ -56,18 +56,6 @@ static_assert(std::is_base_of_v<transcribe_model, ParakeetModel>);
 static_assert(std::is_base_of_v<transcribe_session, ParakeetSession>);
 
 ParakeetSession::~ParakeetSession() {
-    // Tear down per-call compute state before the model's backend plan
-    // (which outlives the context): scheduler, then context.
-    if (sched != nullptr) {
-        safe_sched_free(sched);
-        sched = nullptr;
-    }
-    if (compute_ctx != nullptr) {
-        ggml_free(compute_ctx);
-        compute_ctx = nullptr;
-    }
-    encoder_out = nullptr;
-
     // Streaming cache tensors live in their own ggml_context + backend
     // buffer. Free buffer first (may hold a backend ref), then the ctx.
     if (stream_caches.buffer != nullptr) {
@@ -96,6 +84,11 @@ ParakeetSession::~ParakeetSession() {
     stream_caches.initialized = false;
 }
 
+// Base release_scratch has freed sched/compute_ctx; drop what pointed into them.
+void ParakeetSession::on_scratch_released() noexcept {
+    encoder_out = nullptr;
+}
+
 ParakeetModel::~ParakeetModel() {
     // Teardown order: ctx_meta → backend_buffer → plan backends. The
     // buffer must be freed before the backends (it holds a backend ref);