HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
ggml-org
ggml
C++2022–2026
ggml-org / ggml

ggml

Tensor library for machine learning

31Distinct people
37Mentions
1Explicit recommenders
15.7KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Tensor library for machine learning

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

If you don't care about the details of how those model servers work, then something that abstracts out the whole process like LM Studio or Ollama is all you need. However, if…

manca used a recommendation phrase. One indexed comment matches. This is a phrase match, not a verdict.

Favorable Commenters praise ggml for its performance improvements on legacy hardware and its minimalist design philosophy. One user explicitly links to the repository as a preferred entry point.

This week’s discussion is favorable. This is not a standing endorsement. Read the supporting reply

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Favorable

Commenters praise ggml for its performance improvements on legacy hardware and its minimalist design philosophy. One user explicitly links to the repository as a preferred entry point.

Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4 · 2 discussions summarized

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 8:59:02 AM UTC.

Ggml v1.0.0 direct repository linkDebated

Users widely praise ggml v1.0.0 and llama.cpp for consistent performance gains on existing hardware and broad compatibility, but a vocal minority criticizes recent architectural changes and build processes as telemetry-heavy or overly complex. This disagreement centers on whether the project remains a simple, open engineering tool or has drifted toward proprietary-style practices that alienate core developers.

68 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4
llama.cpp v1.0 official project website

Read the discussion on HN. A full-thread summary is not available yet.

Mentions over time

HN mentions by year37 dated mentions

Observed mentions: 2022-09-20 13:33:46 UTC to 2026-08-17 19:22:51 UTC.

05101520252022-01-01 00:00:00 UTC to 2023-01-01 00:00:00 UTC (exclusive): 3 mentions; 2 submissions, 1 comments20222023-01-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 23 mentions; 6 submissions, 17 comments2024-01-01 00:00:00 UTC to 2025-01-01 00:00:00 UTC (exclusive): 5 mentions; 1 submissions, 4 comments20242025-01-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 comments2026-01-01 00:00:00 UTC to 2027-01-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments. Incomplete calendar period.2026*

* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
20222022-01-01 00:00:00 UTC2023-01-01 00:00:00 UTC321
20232023-01-01 00:00:00 UTC2024-01-01 00:00:00 UTC23617
20242024-01-01 00:00:00 UTC2025-01-01 00:00:00 UTC514
20252025-01-01 00:00:00 UTC2026-01-01 00:00:00 UTC404
2026 (partial)2026-01-01 00:00:00 UTC2027-01-01 00:00:00 UTC202

What Hacker News says

5 sources
Do you know how much faster llama.cpp would go on something like an Intel Core i9 (has AVX2 but not AVX512) when it's compiled using `cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx`? Are we talking like 10% faster inference, or 100%? Right now I'm reasonably certain llamafile is doing about the best job it can be doing on Intel/AMD, supporting SSSE3-only, AVX-only, and AVX2+F16C+FMA microprocessors at runtime. In fact, there's even an issue with the upstream llama.cpp project where they want to get rid of all the external BLAS dependencies. llama.cpp authors claim their quantization trick has actually enabled them to outdistance things like cuBLAS and I'd assume MKL too, which at best, can only operate on f32 and f16. https://github.com/ggerganov/ggml/issues/293 My concern with M
Read the rest
KL is also that, judging by the llama.cpp README's brief mention of using it, adding support sounds like it'd entail a lot more than just dynamically linking a couple GEMM functions from libmkl.so/dll/dylib. It sounds like we'd have to go all in on some environment shell script and intel compiler. I also remember MKL being a huge pain on the TensorFlow team, since it's about as proprietary as it gets.
In Emacs-copilot: Large language model code completion for Emacs

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.