Skip to content

adding kernels for higher-precision arithmetic emulation

active 2025-03-222026-06-27 (UTC)

Partial coverage11,330 / 12,151 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-222026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
12.1K
Pushes
3.3K
Pull requests
992
Issues
420
Stars
13
Forks
11

Activity over time

Daily event counts in the loaded window

Line chart, 463 days from 2025-03-22 to 2026-06-27. Pushes: 3,291 total, peak 36 in a day. Pull requests: 992 total, peak 24 in a day. Issues: 420 total, peak 16 in a day. Comments: 3,053 total, peak 42 in a day. Stars: 13 total, peak 2 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
fvranicTT1.8K415219629
Copilot947136465
github-actions[bot]7976320460
skotaracTT50415517155
ldjurovicTT3812253457
github-merge-queue[bot]37037000
sstanisicTT3671425089
amahmudTT3642921170
ajankovicTT3192541422
ncvetkovicTT2551101149
nvelickovicTT2542690
markoradosavljevicTT2352011313
amokanTT2341573119
rtawfik0123143177
ndivnicTT2041461816
Aswinmcw176702951
vkrsmanovicTT17276945
rdjogoTT146401147
jasondavies14001595
lpremovicTT133541439

Recent activity

Latest issues, pull requests and releases

  • Issue#320github-actions[bot]2026-06-27 04:26
    [Perf] Create list of investigation points for top 10 LLKs
  • Issue comment#1640amahmudTT2026-06-27 04:16
    Use AI to interleave instructions to avoid NOPs
  • Issue#1657amahmudTT2026-06-27 02:59
    Verify requirement of STALLWAIT between THCON and CFG instructions.
  • Issue#1657amahmudTT2026-06-27 02:58
    Verify requirement of STALLWAIT between THCON and CFG instructions.
  • Issue comment#1655amahmudTT2026-06-27 00:53
    Race conditoin in llk_pack_relu_config while clobbering STACC_RELU_ApplyRelu_ADDR32
  • Issue#1249amahmudTT2026-06-26 03:38
    Using AI check if there is any register access race in llk code among threads
  • Issue#7github-actions[bot]2026-06-22 04:38
    [Test Infra] matmul coverage - sweep through sub block size 1-8
  • Issue#9github-actions[bot]2026-06-22 04:38
    [Test Infra] matmul coverage - sweep L1 accumulation (spill)
  • Issue#1647ndivnicTT2026-06-17 10:00
    Add tt-llk coverage for FR8_NF1x1 unpack AB TensorShape
  • Issue comment#361github-actions[bot]2026-06-17 04:36
    Standardize instruction type for maintainability and readability
  • Issue comment#129github-actions[bot]2026-06-15 04:38
    [Test Infra] Inconclusive Hardware Definition for Packer Format Conversion from Float16_b to Float16_a
  • Pull request#1646abdrassulov2026-06-12 01:40
  • Issue comment#38github-actions[bot]2026-06-08 04:37
    [Test Infra] Documentation for Test Infra
  • Issue comment#233github-actions[bot]2026-06-08 04:37
    Two "iterations" parameters
  • Issue#339github-actions[bot]2026-06-05 04:34
    [ Feature ] higher-precision arithmetic emulation in the matmul unit
  • Issue comment#339github-actions[bot]2026-06-05 04:34
    [ Feature ] higher-precision arithmetic emulation in the matmul unit
  • Issue comment#7github-actions[bot]2026-06-02 04:35
    [Test Infra] matmul coverage - sweep through sub block size 1-8
  • Issue#290github-actions[bot]2026-05-30 04:26
    Review transpose_dest API
  • Issue comment#1283github-actions[bot]2026-05-24 04:32
    Add stallwaits to uninits and reconfigs
  • Issue#225github-actions[bot]2026-05-18 04:34
    sin and cos implementations different from ones in tt-metal, metal being more precise
  • Issue comment#709github-actions[bot]2026-05-17 04:29
    Add support for fp8 formats
  • Issue comment#1121github-actions[bot]2026-05-17 04:29
    Expand pack test to support face_r_dim < 16 and num_faces = 1 and num_faces = 2.
  • Issue#732halghTT2026-05-14 20:33
    Wormhole unpack_tilize fails with num_faces = 1 (integer division bug)
  • Issue#131github-actions[bot]2026-05-13 04:24
    [Perf] Untilize OP Utilization
  • Issue comment#115github-actions[bot]2026-05-13 04:24
    Suspected compute kernel issue when scalling behond 1 tile

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 13 stars here means stars gained during the window, not the repo's star count.