Skip to content

微软官方降低AI部署门槛项目

Python · active 2024-10-172026-08-09 (UTC)

Partial coverage14,200 / 17,110 hourly files (83%) · 2 absent upstream · 2,910 failed, retryable2024-08-282026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
19.6K
Pushes
39
Pull requests
69
Issues
140
Stars
17.5K
Forks
1.4K

Activity over time

Daily event counts in the loaded window

Line chart, 662 days from 2024-10-17 to 2026-08-09. Pushes: 39 total, peak 17 in a day. Pull requests: 69 total, peak 5 in a day. Issues: 140 total, peak 12 in a day. Comments: 366 total, peak 46 in a day. Stars: 17,503 total, peak 1,753 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

Recent activity

Latest issues, pull requests and releases

  • Issue comment#501Jah-yee2026-07-13 18:24
    feat: add --skip-gguf-install flag to avoid unconditional pip install
  • Issue comment#567peder19812026-06-07 01:39
    Add L1–L5 algebraic kernels for CPU-only 1.58-bit inference (Walsh–Hadamard, ACDC, tropical sparse, holographic memory) with property-based tests, air-gapped boot validation, and D4 persona documentation
  • Issue comment#567microsoft-github-policy-service[bot]2026-06-07 01:31
    Add L1–L5 algebraic kernels for CPU-only 1.58-bit inference (Walsh–Hadamard, ACDC, tropical sparse, holographic memory) with property-based tests, air-gapped boot validation, and D4 persona documentation
  • Issue comment#562isHuangXin2026-05-21 06:58
    [feat] Add GGUF conversion and inference support for BitNet embedding 270m (Gemma3)
  • Pull request#558isHuangXin2026-05-18 04:05
  • Issue comment#551Jozeh2026-05-03 12:32
    Fix Word Salad (Tensor Corruption) on ARM Devices for i2_s Quantization
  • Issue comment#549EthanPeng-20482026-04-28 12:23
    Fix Compile Error on Windows
  • Issue comment#551betovildoza2026-04-26 19:24
    Fix Word Salad (Tensor Corruption) on ARM Devices for i2_s Quantization
  • Issue comment#513juantellez2026-04-26 16:13
    Windows Compilation Fails: CMake errors in setup_env and missing `const` in ggml-bitnet-mad
  • Issue comment#548xxxn3m3s1sxxx2026-04-19 17:41
    [AUDIT-REF-205] ATLAS Ternary Packer - 16x GGUF Compression
  • Issue comment#548xxxn3m3s1sxxx2026-04-19 16:41
    [AUDIT-REF-205] ATLAS Ternary Packer - 16x GGUF Compression
  • Issue comment#547stackblogger2026-04-18 18:21
    [Bug]: i2_s quantization produces garbage output on x86 CPUs without AVX2 (Missing fallback)
  • Issue#547ViniciusSchererDeOliveira2026-04-18 04:20
    [Bug]: i2_s quantization produces garbage output on x86 CPUs without AVX2 (Missing fallback)
  • Issue comment#475Gujiassh2026-04-11 06:24
    fix: resolve BitNet perplexity defaults from the script dir
  • Issue comment#528microsoft-github-policy-service[bot]2026-04-03 18:18
    Add Metal backend for Apple Silicon inference
  • Issue#527arlm2026-04-03 16:25
    Open WebUI support
  • Issue comment#432arlm2026-04-03 16:25
    Feature request: document/support llama-server HTTP endpoint for OpenAI-compatible serving
  • Issue comment#519jtwolfe2026-04-03 03:07
    Change y_col to const int8_t pointer
  • Issue comment#480thewillwillhelp2026-04-02 20:13
    I installed it on Ubuntu Linux. Here some common help with that...
  • Pull request#519ranjanprj2026-03-30 08:47
  • Issue comment#517vitorgamer582026-03-30 02:53
    llama-server ignores bitnet-b1.58.rope.freq_base metadata, causing NaN in softmax. llama-cli works correctly.
  • Issue comment#508raphaelbgr2026-03-23 07:44
    fix: add missing pre-tokenizer type for GPT-2 BPE models
  • Issue comment#407darkedges2026-03-22 01:00
    Compiler error
  • Pull request#504mvanhorn2026-03-21 15:37
  • Issue comment#335Ogiwara-CostlierRain4642026-03-21 02:18
    Support M≥2 on ladder_int8xint2_kernel

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 17,503 stars here means stars gained during the window, not the repo's star count.