Add support for quantized qwen2-0.5b #128
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Member
CharlieFRuan left a comment
CharlieFRuan left a comment There was a problem hiding this comment.
Took a look, this model is compiled with prefill chunk size 2k. Could you change the file name to Qwen2-0.5B-Instruct-q4f16_1-ctx4k_cs2k-webgpu.wasm? Thanks!
Contributor Author
| I have renamed as suggested. By the way, what is prefill chunk size and how does it relate to memory usage and performance? |
Member
| Thanks! Say prefill chunk size is 2k, if a prompt is 4k, it will be prefilled twice instead of all at once. This helps reduce the size of the intermediate buffer for the matrix multiplication. |
CharlieFRuan pushed a commit to mlc-ai/web-llm that referenced this pull request Jun 27, 2024
Add quantized(q4f16) qwen2-0.5b to the list of supported models. [PR](mlc-ai/binary-mlc-llm-libs#128) must be merged before merging this.
jingyi-zhao-01 pushed a commit to jingyi-zhao-01/web-llm that referenced this pull request Dec 8, 2024
Add quantized(q4f16) qwen2-0.5b to the list of supported models. [PR](mlc-ai/binary-mlc-llm-libs#128) must be merged before merging this.
atebites-hub pushed a commit to atebites-hub/web-llm that referenced this pull request Oct 4, 2025
Add quantized(q4f16) qwen2-0.5b to the list of supported models. [PR](mlc-ai/binary-mlc-llm-libs#128) must be merged before merging this.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
Add support for quantized(q4f16) qwen2-0.5b . Wasm library taken from https://huggingface.co/julientfai/Qwen2-0.5B-Instruct-q4f16_1-Opilot/resolve/main/Qwen2-0.5B-Instruct-q4f16_1-webgpu.wasm?download=true