Skip to content

Sync WebGPU bridge to llama.cpp b9016 #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
leehack merged 3 commits into from
May 8, 2026
Merged

Sync WebGPU bridge to llama.cpp b9016 #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4a1abc4
chore: sync bridge to llama.cpp b9016
leehack May 8, 2026
4048425
Add web bridge native load option parity
leehack May 8, 2026
d28fbd7
Merge remote-tracking branch 'origin/main' into sync-webbridge-b9016
leehack May 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ jobs:
name: Build WebGPU Bridge (WASM)
runs-on: ubuntu-latest
env:
LLAMA_CPP_TAG: b8157
LLAMA_CPP_TAG: b9016
steps:
- uses: actions/checkout@v4

Expand All @@ -27,19 +27,26 @@ jobs:
- name: Build bridge artifacts
env:
OUT_DIR: ${{ runner.temp }}/webgpu_bridge_dist
WEBGPU_BRIDGE_BUILD_MEM64: 1
run: ./scripts/build_bridge.sh

- name: Verify outputs
run: |
test -f "${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_bridge.js"
test -f "${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_bridge_worker.js"
test -f "${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core.js"
test -f "${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core.wasm"
test -f "${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core_mem64.js"
test -f "${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core_mem64.wasm"

- name: Upload bridge artifacts
uses: actions/upload-artifact@v4
with:
name: webgpu-bridge-dist
path: |
${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_bridge.js
${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_bridge_worker.js
${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core.js
${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core.wasm
${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core_mem64.js
${{ runner.temp }}/webgpu_bridge_dist/llama_webgpu_core_mem64.wasm
4 changes: 2 additions & 2 deletions .github/workflows/publish_assets.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,15 +13,15 @@ on:
llama_cpp_tag:
description: llama.cpp tag to build from
required: true
default: b8157
default: b9016
push:
tags:
- 'v*'

env:
ASSETS_TAG: ${{ github.event_name == 'workflow_dispatch' && inputs.assets_tag || github.ref_name }}
ASSETS_REPO: ${{ github.event_name == 'workflow_dispatch' && inputs.assets_repo || 'leehack/llama-web-bridge-assets' }}
LLAMA_CPP_TAG: ${{ github.event_name == 'workflow_dispatch' && inputs.llama_cpp_tag || 'b8157' }}
LLAMA_CPP_TAG: ${{ github.event_name == 'workflow_dispatch' && inputs.llama_cpp_tag || 'b9016' }}

permissions:
contents: read
Expand Down
34 changes: 4 additions & 30 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,9 @@ find_package(Threads REQUIRED)
set(MTMD_AUDIO_SRC "${LLAMA_CPP_DIR}/tools/mtmd/mtmd-audio.cpp")
set(MTMD_AUDIO_PATCHED "${CMAKE_BINARY_DIR}/generated/mtmd-audio-single-thread.cpp")

file(GLOB LLAMADART_MTMD_MODEL_SOURCES
"${LLAMA_CPP_DIR}/tools/mtmd/models/*.cpp")

file(READ "${MTMD_AUDIO_SRC}" MTMD_AUDIO_CONTENT)
string(FIND "${MTMD_AUDIO_CONTENT}" "4, // n_threads" MTMD_AUDIO_THREAD_MARKER_INDEX)
if (MTMD_AUDIO_THREAD_MARKER_INDEX EQUAL -1)
Expand All @@ -74,39 +77,10 @@ string(REPLACE
file(MAKE_DIRECTORY "${CMAKE_BINARY_DIR}/generated")
file(WRITE "${MTMD_AUDIO_PATCHED}" "${MTMD_AUDIO_CONTENT}")

set(LLAMADART_MTMD_MODEL_SOURCES
"${LLAMA_CPP_DIR}/tools/mtmd/models/cogvlm.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/conformer.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/glm4v.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/internvl.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/kimivl.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/kimik25.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/llama4.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/llava.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/minicpmv.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/pixtral.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/qwen2vl.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/qwen3vl.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/siglip.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/whisper-enc.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/mobilenetv5.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/youtuvl.cpp"
)

set(LLAMADART_MTMD_OPTIONAL_MODEL_SOURCES
"${LLAMA_CPP_DIR}/tools/mtmd/models/nemotron-v2-vl.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/models/paddleocr.cpp"
)

foreach(model_source IN LISTS LLAMADART_MTMD_OPTIONAL_MODEL_SOURCES)
if (EXISTS "${model_source}")
list(APPEND LLAMADART_MTMD_MODEL_SOURCES "${model_source}")
endif()
endforeach()

add_library(llamadart_mtmd STATIC
"${LLAMA_CPP_DIR}/tools/mtmd/mtmd.cpp"
"${MTMD_AUDIO_PATCHED}"
"${LLAMA_CPP_DIR}/tools/mtmd/mtmd-image.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/mtmd-helper.cpp"
"${LLAMA_CPP_DIR}/tools/mtmd/clip.cpp"
${LLAMADART_MTMD_MODEL_SOURCES}
Expand Down
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ This repo includes a wasm build gate in:

- `.github/workflows/ci.yml`

It builds against pinned `llama.cpp` tag `b8157` and uploads build artifacts.
It builds against pinned `llama.cpp` tag `b9016` and uploads build artifacts.

## Publishing

Expand Down Expand Up @@ -93,7 +93,7 @@ Manual override example:
2. Inputs:
- `assets_tag`: `v0.1.5`
- `assets_repo`: `leehack/llama-web-bridge-assets`
- `llama_cpp_tag`: `b8157`
- `llama_cpp_tag`: `b9016`

After publish, assets are CDN-available at:

Expand Down
160 changes: 158 additions & 2 deletions js/llama_webgpu_bridge.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,44 @@ function parsePositiveInteger(value) {
return Math.trunc(numeric);
}

function parseInteger(value, fallback = 0) {
const numeric = Number(value);
if (!Number.isFinite(numeric)) {
return fallback;
}
return Math.trunc(numeric);
}

function parseBooleanFlag(value, fallback = false) {
if (typeof value === 'boolean') {
return value;
}
if (typeof value === 'number' && Number.isFinite(value)) {
return value !== 0;
}
return fallback;
}

function parseOptionalBooleanFlag(value) {
if (typeof value === 'boolean') {
return value ? 1 : 0;
}
if (typeof value === 'number' && Number.isFinite(value)) {
return value !== 0 ? 1 : 0;
}
return -1;
}

function parseEnumValue(value, allowed, fallback) {
const parsed = parseInteger(value, fallback);
return allowed.includes(parsed) ? parsed : fallback;
}

function parsePositiveNumber(value) {
const numeric = Number(value);
return Number.isFinite(numeric) && numeric > 0 ? numeric : 0;
}

function parseTotalFromContentRangeHeader(contentRangeHeader) {
if (typeof contentRangeHeader !== 'string' || contentRangeHeader.length === 0) {
return 0;
Expand Down Expand Up @@ -1329,6 +1367,17 @@ class LlamaWebGpuBridgeRuntime {
this._nGpuLayers = Number.isFinite(config.nGpuLayers)
? Number(config.nGpuLayers)
: -1;
this._nSeqMax = 0;
this._useMmap = false;
this._useMlock = false;
this._flashAttention = -1;
this._cacheTypeK = 1;
this._cacheTypeV = 1;
this._kvUnified = -1;
this._ropeFrequencyBase = 0;
this._ropeFrequencyScale = 0;
this._splitMode = -1;
this._mainGpu = -1;
this._isSafari = isSafariUserAgent(this._config.userAgent ?? globalThis.navigator?.userAgent ?? '');
this._coreVariant = 'uninitialized';
this._preferMemory64 = this._config.preferMemory64 !== false;
Expand Down Expand Up @@ -1963,6 +2012,70 @@ class LlamaWebGpuBridgeRuntime {
}
}

_resolveNativeLoadOptions(options = {}) {
this._nSeqMax = parsePositiveInteger(options.nSeqMax);
this._useMmap = parseBooleanFlag(options.useMmap, false);
this._useMlock = parseBooleanFlag(options.useMlock, false);
this._flashAttention = parseEnumValue(options.flashAttention, [-1, 0, 1], -1);
this._cacheTypeK = parseEnumValue(options.cacheTypeK, [1, 2, 8], 1);
this._cacheTypeV = parseEnumValue(options.cacheTypeV, [1, 2, 8], 1);
this._kvUnified = parseOptionalBooleanFlag(options.kvUnified);
this._ropeFrequencyBase = parsePositiveNumber(options.ropeFrequencyBase);
this._ropeFrequencyScale = parsePositiveNumber(options.ropeFrequencyScale);
this._splitMode = parseEnumValue(options.splitMode, [0, 1, 2, 3], -1);
this._mainGpu = parseInteger(options.mainGpu, -1);
if (this._mainGpu < 0) {
this._mainGpu = -1;
}

const wantsQuantizedKvCache = this._cacheTypeK !== 1 || this._cacheTypeV !== 1;
if (this._flashAttention === 0 && wantsQuantizedKvCache) {
throw new Error(
'Non-F16 KV cache requires flashAttention to be auto or enabled.',
);
}
if (this._flashAttention === -1 && wantsQuantizedKvCache) {
this._flashAttention = 1;
this._runtimeNotes.push('flash_attention:auto_enabled_for_kv_cache');
}
if (this._kvUnified < 0 && this._nSeqMax > 1) {
this._kvUnified = 1;
this._runtimeNotes.push('kv_unified:auto_enabled_for_sequences');
}
}

_nativeLoadOptionValues() {
return [
this._nSeqMax,
this._useMmap ? 1 : 0,
this._useMlock ? 1 : 0,
this._flashAttention,
this._cacheTypeK,
this._cacheTypeV,
this._kvUnified,
this._ropeFrequencyBase,
this._ropeFrequencyScale,
this._splitMode,
this._mainGpu,
];
}

_nativeLoadOptionTypes() {
return [
'number',
'number',
'number',
'number',
'number',
'number',
'number',
'number',
'number',
'number',
'number',
];
}

async _tryLoadModelFromRemoteFetchBackend(core, url, options = {}) {
if (!this._canUseRemoteFetchBackend(options)) {
return { loaded: false, sizeBytes: null };
Expand Down Expand Up @@ -2031,6 +2144,7 @@ class LlamaWebGpuBridgeRuntime {
'number',
'number',
'number',
...this._nativeLoadOptionTypes(),
],
[
remoteFetchUrl,
Expand All @@ -2041,6 +2155,7 @@ class LlamaWebGpuBridgeRuntime {
this._nUbatch,
this._nGpuLayers,
chunkBytes,
...this._nativeLoadOptionValues(),
],
{ async: true },
),
Expand Down Expand Up @@ -2926,6 +3041,8 @@ class LlamaWebGpuBridgeRuntime {
this._nUbatch = this._nBatch;
}

this._resolveNativeLoadOptions(options);

if (Number.isFinite(this._threadPoolSizeHint) && this._threadPoolSizeHint > 0) {
this._pushRuntimeNote(`thread_pool_size:${this._threadPoolSizeHint}`);
}
Expand All @@ -2947,6 +3064,9 @@ class LlamaWebGpuBridgeRuntime {
if (this._nUbatch > 0) {
this._pushRuntimeNote(`n_ubatch:${this._nUbatch}`);
}
if (this._nSeqMax > 0) {
this._pushRuntimeNote(`n_seq_max:${this._nSeqMax}`);
}
if (isCpuModelMode && !Number.isFinite(requestedBatch) && !Number.isFinite(requestedUbatch)) {
this._runtimeNotes.push('cpu_batch_tuned_default');
}
Expand Down Expand Up @@ -3174,7 +3294,16 @@ class LlamaWebGpuBridgeRuntime {
await core.ccall(
'llamadart_webgpu_load_model',
'number',
['string', 'number', 'number', 'number', 'number', 'number', 'number'],
[
'string',
'number',
'number',
'number',
'number',
'number',
'number',
...this._nativeLoadOptionTypes(),
],
[
this._modelPath,
this._nCtx,
Expand All @@ -3183,6 +3312,7 @@ class LlamaWebGpuBridgeRuntime {
this._nBatch,
this._nUbatch,
this._nGpuLayers,
...this._nativeLoadOptionValues(),
],
{ async: true },
),
Expand Down Expand Up @@ -3307,6 +3437,7 @@ class LlamaWebGpuBridgeRuntime {
'number',
'number',
'number',
...this._nativeLoadOptionTypes(),
],
[
reloadUrl,
Expand All @@ -3317,6 +3448,7 @@ class LlamaWebGpuBridgeRuntime {
this._nUbatch,
candidateLayers,
remoteFetchReloadChunkBytes,
...this._nativeLoadOptionValues(),
],
{ async: true },
),
Expand All @@ -3326,7 +3458,16 @@ class LlamaWebGpuBridgeRuntime {
await core.ccall(
'llamadart_webgpu_load_model',
'number',
['string', 'number', 'number', 'number', 'number', 'number', 'number'],
[
'string',
'number',
'number',
'number',
'number',
'number',
'number',
...this._nativeLoadOptionTypes(),
],
[
this._modelPath,
this._nCtx,
Expand All @@ -3335,6 +3476,7 @@ class LlamaWebGpuBridgeRuntime {
this._nBatch,
this._nUbatch,
candidateLayers,
...this._nativeLoadOptionValues(),
],
{ async: true },
),
Expand Down Expand Up @@ -4079,6 +4221,20 @@ class LlamaWebGpuBridgeRuntime {
'llamadart.webgpu.n_threads_batch': String(this._threadsBatch),
'llamadart.webgpu.n_batch': this._nBatch > 0 ? String(this._nBatch) : '',
'llamadart.webgpu.n_ubatch': this._nUbatch > 0 ? String(this._nUbatch) : '',
'llamadart.webgpu.n_seq_max': this._nSeqMax > 0 ? String(this._nSeqMax) : '',
'llamadart.webgpu.flash_attention': String(this._flashAttention),
'llamadart.webgpu.cache_type_k': String(this._cacheTypeK),
'llamadart.webgpu.cache_type_v': String(this._cacheTypeV),
'llamadart.webgpu.kv_unified':
this._kvUnified >= 0 ? String(this._kvUnified) : '',
'llamadart.webgpu.rope_freq_base':
this._ropeFrequencyBase > 0 ? String(this._ropeFrequencyBase) : '',
'llamadart.webgpu.rope_freq_scale':
this._ropeFrequencyScale > 0 ? String(this._ropeFrequencyScale) : '',
'llamadart.webgpu.split_mode':
this._splitMode >= 0 ? String(this._splitMode) : '',
'llamadart.webgpu.main_gpu':
this._mainGpu >= 0 ? String(this._mainGpu) : '',
'llamadart.webgpu.thread_pool_size':
Number.isFinite(this._threadPoolSizeHint) && this._threadPoolSizeHint > 0
? String(this._threadPoolSizeHint)
Expand Down
Loading
Loading