# LocalAI v4.6.0 - Product: LocalAI (https://whatsnew.fyi/product/localai) - Vendor: LocalAI - Date: 2026-07-04 - Version: v4.6.0 - Original notes: https://github.com/mudler/LocalAI/releases/tag/v4.6.0 - Permalink: https://whatsnew.fyi/product/localai/releases/v4.6.0 What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog. Reuse: release facts (products, versions, dates, links, CVE ids and flags) are open data under CC BY 4.0, from the API at https://whatsnew.fyi/api/v1 or the nightly dataset at https://github.com/whatsnew-fyi/dataset. The summaries, labels and curation are © What's New: quote freely with attribution and a link back; wholesale republication of them is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'. --- Changes to check: - **Behavior changed:** `POST /backends/apply` (inferred by a model) - **Behavior changed:** `swa_full` (inferred by a model) - **Behavior changed:** `realtime session warm-up` (inferred by a model) - **fixed** — AMD ROCm ggml audio backends now compile with -DGGML_HIP=ON and link HIP for real GPU offload - **fixed** — hipBLASLt kernel-tuning data (TensileLibrary files) is now bundled and HIPBLASLT_TENSILE_LIBPATH is exported - **fixed** — rocm-vllm backend now installs from the AMD ROCm wheel index instead of the CUDA-only PyPI wheel - **fixed** — ASIC ID table (amdgpu.ids) is now symlinked so compute-only hipblas images can find it - **added** — Realtime sessions eagerly warm the entire pipeline (VAD, ASR, LLM, TTS) at session start - **added** — New POST /backend/load and POST /v1/backend/load API endpoints to load models into memory - **added** — Load into memory UI button in the built-in chat interface - **added** — Chat forking capability allowing regeneration of any assistant answer, branching from any turn, duplicating conversations, and copying as Markdown - **fixed** — Dead worker no longer pins the per-model PostgreSQL advisory lock during distributed model loads - **fixed** — Backend workers now self-terminate on parent death instead of holding VRAM - **added** — Prometheus counter localai_pii_events_total for tracking PII detections, masks, and blocks - **fixed** — Gallery config URL fetches are now validated against private, loopback, link-local, and cloud-metadata addresses to prevent SSRF - **changed** — POST /backends/apply and LOCALAI_EXTERNAL_BACKENDS no longer re-pull already-installed backends unless force: true is specified - **fixed** — Non-streaming vLLM tool calls are now restored - **fixed** — MLX and Python backends now decode tool-call arguments for chat templates and split closing-only reasoning blocks #### 🎉 LocalAI 4.6.0 Release! 🚀




LocalAI 4.6.0 is out! This is a reliability-focused release: AMD ROCm backends now run on-GPU at full speed, distributed model loads no longer wedge when a worker dies, and realtime sessions warm up predictably. It also brings conversation forking to the built-in chat UI, a Prometheus counter for PII/audit events, and an SSRF fix for the model gallery. **Highlights:** - 🔴 **AMD ROCm runs correctly** - ggml audio backends offload to the GPU, hipBLASLt kernel-tuning data is bundled (no more slow generic kernels), `rocm-vllm` installs the right wheel, and the ASIC ID table is found. - 🎙️ **Predictable realtime** - sessions eagerly warm the whole pipeline (VAD, ASR, LLM, TTS) up front, so the first turn no longer pays per-model cold-start stalls, plus a new `POST /backend/load` API and "Load into memory" UI button. - 🌿 **Forking chat** - retry *any* assistant answer, branch a new chat from any point, duplicate, or copy the whole conversation, directly in the built-in UI. - 🛡️ **Distributed hardening** - a dead worker can no longer pin the model-load advisory lock (the ~15-minute wedge is gone), and orphaned backend workers self-terminate instead of holding VRAM. - 📊 **PII/audit metrics** - PII detections/masks/blocks are exported as a Prometheus counter, so you can alert when the filter stops firing. - 🔒 **Gallery SSRF fix** - `POST /models/apply` config-URL fetches are validated against private/loopback/metadata addresses. Plus idempotent backend installs, tool-calling and reasoning fixes across the vLLM and Python/MLX backends, cloud-proxy compatibility with the newest reasoning models, and the usual set of dependency updates. --- ##### 📌 TL;DR | Area | Summary | |------|---------| | 🔴 **AMD ROCm reliability** | ggml audio backends now compile with `-DGGML_HIP=ON` and link HIP (real GPU offload); hipBLASLt `TensileLibrary` data bundled + `HIPBLASLT_TENSILE_LIBPATH` exported; `rocm-vllm` installs from the AMD wheel index on Python 3.12; `amdgpu.ids` symlinked so the ASIC table is found. | | 🎙️ **Realtime warm-up + load API** | Sessions block-warm the full pipeline at start (errors surface up front); new `POST /backend/load` / `POST /v1/backend/load`, a "Load into memory" UI action, and a `load_model` MCP tool. Opt out per pipeline with `disable_warmup: true`. | | 🌿 **Forking chat** | Regenerate any assistant answer (not just the last), branch a new chat from any turn, duplicate a chat, or copy it as Markdown - all client-side in the React UI. | | 🛡️ **Process & distributed lifecycle** | A dead worker no longer pins the per-model PostgreSQL advisory lock (bounded load ceiling + context-scoped `lock_timeout`); backend workers self-terminate on parent death (`LOCALAI_BACKEND_PARENT_WATCH`); the watchdog stops logging optional `Free()` as an error. | | ⚙️ **Idempotent backend installs** | `POST /backends/apply` and the `LOCALAI_EXTERNAL_BACKENDS` boot loop no longer re-pull an already-installed backend unless `force: true`. | | 📊 **PII/audit Prometheus counter** | `localai_pii_events_total{kind,origin,action,direction}` on `/metrics`, complementing the `/api/pii/events` ring buffer. | | 🔒 **Gallery SSRF hardening** | Gallery config URL fetches run through `ValidateExternalURL`, blocking private, loopback, link-local, and cloud-metadata addresses. | | 🧩 **Tool-calling & reasoning fixes** | Non-streaming vLLM tool calls restored; MLX/Python backends decode tool-call arguments for chat templates and split closing-only `` reasoning blocks. | --- ##### 🚀 New Features & Major Enhancements ###### 🔴 AMD ROCm backends run correctly on-GPU Four coupled fixes make ROCm/hipBLAS backends actually run on AMD hardware, and at full speed, instead of silently falling back _[Truncated at 4000 characters — full notes: https://github.com/mudler/LocalAI/releases/tag/v4.6.0]_