anyformer 0.4.20 → 0.4.21

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## 0.4.21 — 2026-10-31
+
+### Changed
+- diskformer pin cefebc7 → 7962912 (v0.6.20: run-time LoRA in every native MoE engine through `engines/lora.js`).
+  The `diskformer` back end now takes `adapter` on Gemma 4 26B and Qwen3.6 35B too. diskformer's gates (plain /
+  adapter / plain again, against llama-server --lora on the same file): Gemma 4 26B 9/9, 8/9, 9/9; Qwen3.6 35B 6/9,
+  9/9, 6/9. Adapters on routed experts are refused with an error. MiniCPM-V, Clover, Flint and Ling take no adapter,
+  so an `adapter` drops `diskformer` from their plans.
+
+### Not yet verified
+- No browser run of an adapter on Gemma 4 or Qwen3.6 through anyformer: no adapter GGUF for either is in the catalog.
+
 ## 0.4.20 — 2026-10-31
 
 ### Added
@@ -24,6 +36,16 @@
   `alwaysThinks` and `thinkInPrompt`) returns only the answer in `text`, and the reasoning in `reasoning`.
 - diskformer pin 317d2a0 → cefebc7 (v0.6.19: run-time LoRA in `lfm2_moe_ssd.js`).
 
+### Verified (after the npm publish, on the published code)
+- `tools` on LFM2.5 230M (`localmind`, local file): `get_weather` {"city":"Paris"} parsed from the bare call list;
+  after the tool result, an answer with 18°C and clear sky.
+- `tools` on `LFM2_5_24B_PI` (`diskformer`, run-time adapter, base GGUF and adapter from local files, 13:31 IST): the
+  first turn's text is empty (reasoning in `reasoning`) with `get_weather` {"city":"Paris"} as `toolCalls`; then
+  "The current weather in Paris is **clear skies** with a temperature of **18°C**."
+- `chat?entry=chat.LFM2_5_24B_PI&turns=4` on the same engine (by 13:41 IST): PASS, 4/4 turns on topic with no
+  reasoning in `text`; load 50 s from OPFS. The page's tok/s (about 2.5) counts only answer tokens after the hidden
+  reasoning, so it is not a decode speed.
+
 ## 0.4.19 — 2026-10-31
 
 ### Changed

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "anyformer",
-  "version": "0.4.20",
+  "version": "0.4.21",
   "description": "One call to run a model in a browser tab: anyformer reads the Hub repo, probes the browser, and picks the back end (transformers.js, LocalMind's WebGPU kernels, diskformer, kohra) that fits the model's format, architecture and your GPU budget.",
   "type": "module",
   "main": "./index.js",

package/src/backends/diskformer.js

@@ -11,11 +11,15 @@ export const DISKFORMER_MODELS = [
   {
     repo: 'google/gemma-4-26B-A4B-it-qat-q4_0-gguf', file: 'gemma-4-26B_q4_0-it.gguf', size: 14439363584,
     engine: 'gemma4_moe_ssd.js', Engine: 'Gemma4MoeSsd', minBudget: 2.5e9,
+    // LoRA at run time (v0.6.20+, gated against llama-server --lora on the same adapter file).
+    adapters: true,
     speeds: [[2.5e9, 12.4], [4.3e9, 14.2], [7e9, 17.9]],
   },
   {
     repo: 'unsloth/Qwen3.6-35B-A3B-GGUF', file: 'Qwen3.6-35B-A3B-Q8_0.gguf', size: 36903140320,
     engine: 'qwen35_moe_ssd.js', Engine: 'Qwen35MoeSsd', minBudget: 4e9,
+    // LoRA at run time (v0.6.20+, gated against llama-server --lora on the same adapter file).
+    adapters: true,
     speeds: [[4e9, 9.2]],
   },
   // Qwen3.6's language model with a vision encoder (mmproj, ~1.1 GB, loaded on the first image by ensureVision).

package/src/sources.js

@@ -9,6 +9,8 @@ export const PINS = {
   // v0.3.1: seeded block-KV graphs (Nemotron-Labs-Diffusion-3B), chatFormat, split external data; download progress
   // (progress_callback) and the graph files cached in Cache Storage 'kohra-models'.
   kohra: 'bf95d44c3e3cfc001201baa03fa121c2bf9c7d73',
+  // v0.6.20 (7962912): run-time LoRA in every native MoE engine (engines/lora.js): Gemma 4 26B, Qwen3.6 35B, LFM2.5
+  // 24B and Qwen3 (untested); adapters on routed experts are refused. Engines expose addBos from the GGUF.
   // v0.6.19 (cefebc7): run-time LoRA in lfm2_moe_ssd.js (engine.loadAdapter / setAdapter, no reload to switch).
   // v0.6.18 (317d2a0): with thinking off, the llama.cpp chat closes a template's always-open <think> (LFM2.5-24B) and
   // bans the <think> token for the reply.
@@ -31,7 +33,7 @@ export const PINS = {
   // Gemma 4 E2B/E4B and Ternary Bonsai 2) under engines/, and the llama.cpp path under ggml/, which loads split GGUFs
   // and drafters, and reads past 2 GiB (Nemotron 3.5 Bolt E4B needs v0.6.8 or later). The hand engines' ingest
   // streams the GGUF header with progress and resumes a dropped range.
-  diskformer: 'cefebc7c18bf106f82378925bd5650cae4320193',
+  diskformer: '79629125d7a39b13ddcaf74df58262458d8d470e',
 };
 
 const gh = (repo, sha, path) => `https://cdn.jsdelivr.net/gh/NakliTechie/${repo}@${sha}/${path}`;