Skip to content

T-MAC: Table Lookup Makes CPU Great Again for Low-Bit LLM Inference

C++ · active 2024-02-022026-06-07 (UTC)

Complete coverage26,396 / 26,396 hourly files (100%) · 2 absent upstream2023-08-152026-08-18 (UTC)
Events
1.5K
Pushes
99
Pull requests
24
Issues
107
Stars
832
Forks
76

Activity over time

Daily event counts in the loaded window

Line chart, 857 days from 2024-02-02 to 2026-06-07. Pushes: 99 total, peak 6 in a day. Pull requests: 24 total, peak 3 in a day. Issues: 107 total, peak 10 in a day. Comments: 273 total, peak 17 in a day. Stars: 832 total, peak 43 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
kaleid-liner211811995
QingtaoLi13711121
qw1319310022
sunj0104170014
orange-juice1140011
idreamerhx9006
AndreaChiChengdu8004
ma-hang8007
hellangleZ7007
xdd1307005
jixiuy6003
velonica06003
microsoftopensource5500
alter-xp5023
Zijie-Tian5001
nctu65005
ppp-max5002
maxim-saplin5004
tiger-of-shawn5004
caoshijie05015113

Recent activity

Latest issues, pull requests and releases

  • Issue#106Looong012026-02-03 13:41
    Intel & AMD NPU support?
  • Issue comment#105My-captain2026-01-08 03:01
    ModuleNotFoundError: No module named 'torchgen.executorch'
  • Issue#99ali-881232025-09-22 07:30
    Windows11 build llama.cpp CMakeFiles error
  • Issue comment#24lippman11252025-09-19 17:10
    Any plans to merge the latest code of llama.cpp?
  • Issue comment#96kaleid-liner2025-07-03 08:59
    3bit kernel evaluation
  • Issue#97FabianSchuetze2025-06-20 13:10
    Cannt find tvm Libraries
  • Issue#96riteme2025-06-13 08:56
    3bit kernel evaluation
  • Issue#94Singapore-mor2025-06-02 09:38
    how to do the weight permutation
  • Issue comment#91type-shangshu2025-04-16 17:04
    How to change the llama.cpp to T-mac(LUT-based)?I successfully run the code from the readme in my M1 computer, but the method is using llama.cpp don't the T-mac(LUT-based) from the thesis.
  • Issue comment#91Promortyus2025-04-16 08:04
    How to change the llama.cpp to T-mac(LUT-based)?I successfully run the code from the readme in my M1 computer, but the method is using llama.cpp don't the T-mac(LUT-based) from the thesis.
  • Issue comment#88gogogo662025-04-11 08:44
    AttributeError: module 'tvm.auto_scheduler._ffi_api' has no attribute 'RandomModel'
  • Issue#92Heinzt3052025-04-06 14:23
    Does T-MAC Support Per-Channel Quantization?
  • Issue comment#91jixiuy2025-04-02 04:21
    How to change the llama.cpp to T-mac(LUT-based)?I successfully run the code from the readme in my M1 computer, but the method is using llama.cpp don't the T-mac(LUT-based) from the thesis.
  • Issue#91jixiuy2025-04-02 04:14
    How to change the llama.cpp to T-mac(LUT-based)?I successfully run the code from the readme in my M1 computer, but the method is using llama.cpp don't the T-mac(LUT-based) from the thesis.
  • Issue#90jixiuy2025-04-02 04:11
    Running STEP.6: Run inference Error
  • Issue comment#90jixiuy2025-04-02 04:11
    Running STEP.6: Run inference Error
  • Issue comment#90jixiuy2025-04-01 12:00
    Running STEP.6: Run inference Error
  • Issue#90jixiuy2025-04-01 11:54
    Running STEP.6: Run inference Error
  • Issue comment#85alter-xp2025-03-27 07:02
    Segmentation fault on Raspberry Pi 5 with the official example
  • Issue comment#85xxxxyu2025-03-27 06:54
    Segmentation fault on Raspberry Pi 5 with the official example
  • Issue#89NielsRogge2025-03-26 09:20
    Release artifacts (models, dataset) on Hugging Face
  • Issue comment#85alter-xp2025-03-20 01:37
    Segmentation fault on Raspberry Pi 5 with the official example
  • Pull request#87alter-xp2025-03-18 07:23
  • Issue#88Promortyus2025-03-17 07:59
    AttributeError: module 'tvm.auto_scheduler._ffi_api' has no attribute 'RandomModel'
  • Issue comment#85QingtaoLi12025-02-24 05:39
    Segmentation fault on Raspberry Pi 5 with the official example

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 832 stars here means stars gained during the window, not the repo's star count.