[webgpu] Implement SubGroupMatrix based MatMulNBits for Metal - #23729
Merged
Guenther Schmuelling (guschmue) merged 15 commits intoFeb 21, 2025
Conversation
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Sushanth Rajasankar (sushraja-msft)
marked this pull request as ready for review
February 19, 2025 00:30
Sushanth Rajasankar (sushraja-msft)
force-pushed
the
user/sushraja/subgroupMatrix
branch
from
February 19, 2025 20:37
e90b823 to
09e30be
Compare
Sushanth Rajasankar (sushraja-msft)
requested a review
from Guenther Schmuelling (guschmue)
February 19, 2025 23:31
Sushanth Rajasankar (sushraja-msft)
force-pushed
the
user/sushraja/subgroupMatrix
branch
from
February 20, 2025 00:32
92db1cf to
f7ddbb0
Compare
Contributor
|
the ort web pipeline compiles webgpu ep with emscripten which fails with: Possible the headerfile that comes with emscripten doesn't know that featurename yet Maybe use |
Contributor
Author
done ! |
Contributor
|
/azp run Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline,CoreML CI Pipeline,Linux DNNL CI Pipeline,Linux MIGraphX CI Pipeline,Linux ROCm CI Pipeline |
|
Azure Pipelines successfully started running 7 pipeline(s). |
Guenther Schmuelling (guschmue)
approved these changes
Feb 21, 2025
Guenther Schmuelling (guschmue)
deleted the
user/sushraja/subgroupMatrix
branch
February 21, 2025 17:23
Guenther Schmuelling (guschmue)
pushed a commit
that referenced
this pull request
Mar 6, 2025
### Description Recent progress with SubGroupMatrix prototype in Dawn https://issues.chromium.org/issues/348702031, exposes SIMD-Group Matrix Functions to webgpu. This shader implements a matmulnbits using that primitive. Observed perf gains, in terms of LLM inference speed, prefill perf for Phi 3.5 for a 1K token prefill see 3x improvement. 5.4s from 15s. With Changes ``` ./model_benchmark -i ~/Phi-3.5-mini-instruct-onnx-web -l 1000 Batch size: 1, prompt tokens: 1001, tokens to generate: 128 Prompt processing (time to first token): avg (us): 5.42498e+06 <<< SubGroupMatrix 5.4s avg (tokens/s): 184.517 p50 (us): 5.41982e+06 stddev (us): 12023.8 n: 5 * 1001 token(s) Token generation: avg (us): 91138.5 avg (tokens/s): 10.9723 p50 (us): 89488.5 stddev (us): 35136.2 n: 635 * 1 token(s) ``` Baseline ``` ./model_benchmark -i ~/Phi-3.5-mini-instruct-onnx-web -l 1000 Batch size: 1, prompt tokens: 1001, tokens to generate: 128 Prompt processing (time to first token): avg (us): 1.45507e+07 <<< Baseline 14.5s avg (tokens/s): 68.7938 p50 (us): 1.45413e+07 stddev (us): 22208.9 n: 5 * 1001 token(s) Token generation: avg (us): 94109.8 avg (tokens/s): 10.6259 p50 (us): 89660 stddev (us): 61579 n: 635 * 1 token(s) ```
Ashrit Shetty (ashrit-ms)
pushed a commit
that referenced
this pull request
Mar 17, 2025
### Description Recent progress with SubGroupMatrix prototype in Dawn https://issues.chromium.org/issues/348702031, exposes SIMD-Group Matrix Functions to webgpu. This shader implements a matmulnbits using that primitive. Observed perf gains, in terms of LLM inference speed, prefill perf for Phi 3.5 for a 1K token prefill see 3x improvement. 5.4s from 15s. With Changes ``` ./model_benchmark -i ~/Phi-3.5-mini-instruct-onnx-web -l 1000 Batch size: 1, prompt tokens: 1001, tokens to generate: 128 Prompt processing (time to first token): avg (us): 5.42498e+06 <<< SubGroupMatrix 5.4s avg (tokens/s): 184.517 p50 (us): 5.41982e+06 stddev (us): 12023.8 n: 5 * 1001 token(s) Token generation: avg (us): 91138.5 avg (tokens/s): 10.9723 p50 (us): 89488.5 stddev (us): 35136.2 n: 635 * 1 token(s) ``` Baseline ``` ./model_benchmark -i ~/Phi-3.5-mini-instruct-onnx-web -l 1000 Batch size: 1, prompt tokens: 1001, tokens to generate: 128 Prompt processing (time to first token): avg (us): 1.45507e+07 <<< Baseline 14.5s avg (tokens/s): 68.7938 p50 (us): 1.45413e+07 stddev (us): 22208.9 n: 5 * 1001 token(s) Token generation: avg (us): 94109.8 avg (tokens/s): 10.6259 p50 (us): 89660 stddev (us): 61579 n: 635 * 1 token(s) ```
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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.
Description
Recent progress with SubGroupMatrix prototype in Dawn https://issues.chromium.org/issues/348702031, exposes SIMD-Group Matrix Functions to webgpu. This shader implements a matmulnbits using that primitive.
Observed perf gains, in terms of LLM inference speed, prefill perf for Phi 3.5 for a 1K token prefill see 3x improvement. 5.4s from 15s.
With Changes
Baseline