Alternatives
Products that do what fast_trimul does
A drop-in library for fast Triangle Multiplicative Updates
- 1
- 2
- 3SC
2021 · blog.tonari.no
- 4UA
Hey HN! After using a combination of Unsloth and Axolotl a lot, and finding it generally painful to figure out the right performance tuning for things like batch sizing and multi-GPU sharding, I wrote a small Python lib that sets up known-good LoRA training configurations for Llama 3.1 8B and 70B Instruct, and includes helpers for distilling from larger models or training on serverless finetuning platforms, and includes a walkthrough for distilling DeepSeek-R1 into a Llama 3.1 8B LoRA... But you can use it for pretty much any finetuning task, not just distilling large models!
2025 · github.com
- 5E0
2017 · github.com
- 6T5
2021 · tensorbase.io
- 7TL
2022 · github.com
- 8LW
2017 · github.com
- 9LA
tl;dr I'm developing an incredibly fast library for arrays and mathematics, and I've implemented a few new features and made some improvements. I'd love for you to check it out! Links: GitHub: https://github.com/LibRapid/librapid/ Documentation: https://librapid.readthedocs.io/en/latest/ Discord: https://discord.com/invite/cGxTFTgCAC Hey everyone! I am the lead developer of LibRapid (https://github.com/LibRapid/librapid/), a high-performance C++ library for array manipulation and mathematics. I've…
2023
- 10SA
2018 · github.com
- 11AA
2017 · github.com
- 12AD
2018 · github.com
- 13OS
2013 · yeppp.info
- 14AS
2020 · github.com
- 15SS
I'm developing a storage system for versioning data at the subfile level, especially well suited for SSDs due to its log-structured COW nature. It implements a novel versioning algorithm called sliding snapshot, a diff-algorithm which makes use of our stable record-identifiers and optionally hashes, another diff algorithm for importing similar XML-documents as a versioned resource as well as novel XPath axis to navigate not only in space, but also in time. Recently, I've implemented a higher level, asynchronous REST-API with Kotlin (Coroutines) and Vert.x in a seperate module. The system is…
2018
- 16KP
I thought it'd be interesting to use Linux PSI (Pressure Stall Information) for an LLM runtime to trim the KV cache. This is mainly useful imo for edge devices like the Jetson Orin super nano kit which have unified memory. I haven't benched much, but plan to do so more over time and see if I can make a real use of it as I run local LLMs. Let me know if it makes sense :P (I of course vibed this idea)
Jun 2026 · github.com
- 17RA
We built RapidFire AI, an open-source Python tool to speed up LLM fine-tuning and post-training with a powerful level of control not found in most tools: Stop, resume, clone-modify and warm-start configs on the fly—so you can branch experiments while they’re running instead of starting from scratch or running one after another. - Works within your OSS stack: PyTorch, HuggingFace TRL/PEFT), MLflow. - Hyperparallel search: launch as many configs as you want together, even on a single GPU - Dynamic real-time control: stop laggards, resume them later to revisit, branch promising configs in…
Sep 2025 · github.com
- 18LS
Earlier this year, I took a month to reexamine my coding habits and rethink some past design choices. I hope to rewrite and improve my FOSS libraries this year, and I needed answers to a few questions first. Perhaps some of these questions will resonate with others in the community, too. - Are coroutines viable for high-performance work? - Should I use SIMD intrinsics for clarity or drop to assembly for easier library distribution? - Has hardware caught up with vectorized scatter/gather in AVX-512 & SVE? - How do secure enclaves & pointer tagging differ on Intel, Arm, & AMD? - What's…
2025 · github.com
- 19SF
Hey HN! We've just open-sourced Semble, a fast and accurate code search library built for agents. We're also releasing potion-code-16M, a small code-specialized static embedding model that powers it. Most embedding-based code search methods are either too slow to index on demand or need GPU infrastructure, while grep-style retrieval methods often cannot find the relevant content. Semble combines the speed and quality benefits of both, so agents waste less time and fewer tokens exploring. Main features: - Fast: indexes a full codebase in ~250 ms and answers queries in ~1.5 ms, all on CPU…
Apr 2026 · github.com
- 20AN
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026
- 21IB
I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things. The stack is Phoenix/Oban on the orchestrator side, and Python/FastAPI/Instructor for the AI workers. Happy to answer any questions about the architecture,…
Apr 2026 · qwelian.com
- 22FN
"I wanted to see if I could optimize the dequantization bottleneck during 4-bit LLM inference. By writing a custom kernel in Triton to optimize memory access patterns, I managed to get up to a 1.41x speedup over the standard bitsandbytes implementation. Check out the source code and benchmarks, feedback is highly appreciated!"
Jul 2026 · github.com
- 23AA
Apr 2026 · veniatyrannus993225.substack.com
- 24LC
2021 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →