@simulatte/doppler 0.1.0 → 0.1.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +27 -23
  2. package/package.json +3 -5
package/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # @simulatte/doppler
2
2
 
3
- Browser-native inference engine for local AI workloads.
3
+ Inference and training on raw WebGPU. Pure JS + WGSL.
4
4
 
5
5
  **[Live Demo](https://d4da.com)** · **[npm](https://www.npmjs.com/package/@simulatte/doppler)** · **[simulatte.world](https://simulatte.world)**
6
6
 
@@ -10,7 +10,7 @@ Browser-native inference engine for local AI workloads.
10
10
  npm install @simulatte/doppler
11
11
  ```
12
12
 
13
- ## Quick Start
13
+ ## Quick start
14
14
 
15
15
  ```js
16
16
  import { doppler } from '@simulatte/doppler';
@@ -22,38 +22,35 @@ for await (const token of model.generate('Hello, world')) {
22
22
  }
23
23
  ```
24
24
 
25
- That's it. Streaming is the default. See [more examples](#more-examples) below or the full [API contract](docs/doppler-api-contract.md).
25
+ Tokens stream from a native `AsyncGenerator`. See [more examples](#more-examples) below or the full [API contract](docs/doppler-api-contract.md).
26
26
 
27
- ## Features
27
+ ## Why Doppler
28
28
 
29
- - WebGPU-accelerated inference in browser and Node — no WASM bridge
30
- - Native `for await` streaming — not callbacks
31
- - Sharded weight loading via OPFS
32
- - LoRA adapter hot-swap at runtime
33
- - Quantized model support (Q4K, Q8, F16)
34
- - Multi-model with independent instances
35
- - Kernel hot-swap (prefill/decode paths)
36
- - Reproducible benchmark tooling
37
- - Auditable kernel execution tracing
29
+ **JS → WGSL → WebGPU.** Direct JavaScript orchestration into native WebGPU kernels, avoiding ONNX runtimes, WASM blobs, and bridge layers.
38
30
 
39
- ## Browser Support
31
+ **`for await` streaming.** Generation uses a native `AsyncGenerator` that fits normal app control flow.
40
32
 
41
- - Chrome / Edge 113+ (WebGPU required)
42
- - Firefox (behind flag, WebGPU support varies)
43
- - Safari (WebGPU support in progress)
33
+ **LoRA hot-swap.** Swap adapters at runtime without reloading the base model.
44
34
 
45
- ---
35
+ **Independent model instances.** Run multiple models concurrently. Each owns its pipeline, buffers, and KV cache.
46
36
 
47
37
  ## Evidence
48
38
 
49
- Lower is better, comparing per-phase latency by workload.
50
-
51
39
  ![Phase-latency comparison on one workload across models](benchmarks/vendors/results/compare_1b_multi-workload_favorable_phases.svg)
52
40
 
53
- Snapshot artifact:
54
- - [g3-p064-d064-t0-k1.apple-m3pro.compare.json](benchmarks/vendors/fixtures/g3-p064-d064-t0-k1.apple-m3pro.compare.json)
41
+ Snapshot artifacts:
42
+ - [g3-1b-p064-d064-t0-k1.compare.json](benchmarks/vendors/fixtures/g3-1b-p064-d064-t0-k1.compare.json)
43
+ - [lfm2-5-1-2b-p064-d064-t0-k1.compare.json](benchmarks/vendors/fixtures/lfm2-5-1-2b-p064-d064-t0-k1.compare.json)
44
+
45
+ ## Under the hood
46
+
47
+ - Sharded weight loading via OPFS moves multi-GB weights into VRAM without blocking the main thread.
48
+ - Quantized inference paths (Q4K, Q8, F16) support practical model sizes on consumer GPUs.
49
+ - Kernel hot-swap between prefill and decode paths.
50
+ - Config-driven runtime keeps presets, kernel-path selection, and sampling explicit.
51
+ - Reproducible benchmarks expose deterministic knobs and auditable kernel traces.
55
52
 
56
- ## More Examples
53
+ ## More examples
57
54
 
58
55
  ```js
59
56
  // Non-streaming
@@ -80,6 +77,13 @@ for await (const token of doppler('Hello', { model: 'gemma-3-1b' })) {
80
77
  - Runtime config contract: [docs/config.md](docs/config.md)
81
78
  - Architecture: [docs/architecture.md](docs/architecture.md)
82
79
 
80
+ ## Environment requirements
81
+
82
+ - WebGPU-capable browser runtime is required.
83
+ - Chrome / Edge 113+ supported.
84
+ - Firefox support varies (typically behind a flag).
85
+ - Safari support is evolving.
86
+
83
87
  ## License
84
88
 
85
89
  Apache License 2.0 (`Apache-2.0`). See [LICENSE](LICENSE) and [NOTICE](NOTICE).
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@simulatte/doppler",
3
- "version": "0.1.0",
3
+ "version": "0.1.2",
4
4
  "description": "Browser-native WebGPU inference engine for local intent and inference loops",
5
5
  "main": "src/index.js",
6
6
  "types": "src/index.d.ts",
@@ -134,11 +134,9 @@
134
134
  "tools/convert-safetensors-node.js"
135
135
  ],
136
136
  "devDependencies": {
137
+ "@huggingface/transformers": "^3.8.1",
137
138
  "jest": "^30.2.0",
139
+ "onnxruntime-web": "^1.24.1",
138
140
  "playwright": "^1.58.2"
139
- },
140
- "dependencies": {
141
- "@huggingface/transformers": "^3.8.1",
142
- "onnxruntime-web": "^1.24.1"
143
141
  }
144
142
  }