Skip to content

Commit d8f1ecb

Browse files
nachawatinachawati
committed
fix(ci): add tensor-cache.json to webllm model download, bump cache key
1 parent 2dba007 commit d8f1ecb

2 files changed

Lines changed: 2 additions & 1 deletion

File tree

‎.github/workflows/ci.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,7 @@ jobs:
7575
uses: actions/cache@v4
7676
with:
7777
path: packages/ide/models
78-
key: ${{ runner.os }}-qwen3-0.6b-q4f16_1-mlc-v1
78+
key: ${{ runner.os }}-qwen3-0.6b-q4f16_1-mlc-v2
7979
- name: Download WebLLM Model
8080
if: steps.cache-model.outputs.cache-hit != 'true'
8181
run: bash packages/ide/scripts/download-model.sh

‎packages/ide/scripts/download-model.sh‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -20,6 +20,7 @@ WASM_NAME="Qwen3-0.6B-q4f16_1-ctx4k_cs1k-webgpu.wasm"
2020
MODEL_FILES=(
2121
mlc-chat-config.json
2222
ndarray-cache.json
23+
tensor-cache.json
2324
tokenizer.json
2425
tokenizer_config.json
2526
vocab.json

0 commit comments

Comments
 (0)