microsoft / microsoft/BitNet

AVX-512 instructions enable denser packing and more efficient lookups.

Open
#569 10 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
40.3k
Forks
3.7k
PR merge metrics
No merged PRs in 30d

Description

I have an implementation put together here: https://github.com/tommyyliu/lut_mm/blob/master/src/ternary_mm_avx512.cpp

The table has all the dot products with 5 activations instead of just 3. This means that each lookup handles 5 instead of 3, and you can see pretty substantial speedup.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the linked implementation in src/ternary_mm_avx512.cpp and compare its five-activation lookup approach with the corresponding BitNet code. Identify the intended integration point and determine what benchmark or validation would demonstrate the reported speedup; the issue does not name a BitNet file or test that defines completion.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.