Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
181.
▲
New open-source model with 8k context runs on CPU, outperforms GPT-3
(github.com/abacaj)
5 points
sheepscreek
3 years ago
1 comment
182.
▲
Accelerating LLM Serving with Speculative Inference and Token Tree Verification
(github.com/flexflow)
3 points
zhihaojia
3 years ago
1 comment
183.
▲
Hugging Face reverts the license back to Apache 2.0
(github.com/huggingface)
3 points
vmatsiiako
2 years ago
discuss
184.
▲
Fast inference for text models using Rust
(github.com/huggingface)
3 points
l-m-z
3 years ago
discuss
185.
▲
MPT 30B inference code using CPU
(github.com/abacaj)
3 points
djha-skin
3 years ago
discuss
186.
▲
Text to Speech CUDA Programming
(github.com/Saurabh-29)
3 points
Saurabh_29
7 years ago
discuss
187.
▲
Bayesian inference and forecast of Covid-19 in Germany by a Max-Planck-Institute
(github.com/Priesemann-Group)
2 points
freemint
6 years ago
3 comments
188.
▲
Diffbot GraphRAG LLM
(github.com/diffbot)
2 points
miket
a year ago
1 comment
189.
▲
GPT4ALL Python3 Local LLM Conversation Recorder
(github.com/13alvone)
2 points
13alvone
3 years ago
1 comment
190.
▲
Show HN: Bert NLP inference in browser using WebAssembly-SIMD
(github.com/jobergum)
2 points
jkb79
4 years ago
discuss
191.
▲
Private Decentralized Inference on Consumer Hardware [pdf]
(github.com/Layr-Labs)
1 point
doener
a month ago
1 comment
192.
▲
Open Source Stable Diffusion with LCM-LoRA
(github.com/joshfischer1108)
1 point
joshfischer1108
3 years ago
1 comment
193.
▲
Private decentralized inference on consumer hardware [pdf]
(github.com/Layr-Labs)
1 point
andsoitis
2 months ago
discuss
194.
▲
VGGT PyTorch Inference
(github.com/ibaiGorordo)
1 point
Tycho87
a year ago
discuss
195.
▲
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
(github.com/cactus-compute)
776 points
HenryNdubuaku
25 days ago
211 comments
196.
▲
Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
270 points
yujonglee
10 months ago
180 comments
197.
▲
Show HN: Fastify's slow startup is an AJV problem – here's a drop-in fix
2 points
greatvenerable
3 months ago
discuss
198.
▲
Finished a project mixing GNNs, RL, and operations research
(github.com/MehdiZouitine)
1 point
Md_Zouzou
a year ago
1 comment
199.
▲
Show HN: I built an Image Embedding API inspired by text-embedding-inference
(github.com/bernardo-sb)
1 point
bernardo-sb
a year ago
discuss
200.
▲
Show HN: ImageEmbeddingInference – like text-embeddings-inference but for images
(github.com/bernardo-sb)
1 point
bernardo-sb
a year ago
discuss
201.
▲
Show HN: Sightline – Shodan-style search for real-world infra using OSM Data
(github.com/ni5arga)
26 points
ni5arga
4 months ago
1 comment
202.
▲
Ask HN: Are you saving inference costs on GPUs at your company
5 points
idomi
a year ago
1 comment
203.
▲
Show HN: Revibing nanochat's inference model in C++ with ggml
(github.com/k-ye)
5 points
makechan
5 months ago
discuss
204.
▲
Show HN: Letting an LLM write robot programs
(boesch.dev)
3 points
encrux
2 months ago
discuss
205.
▲
Show HN: MLX-Ruby – Ruby Bindings for Apple's MLX ML Framework
(github.com/skryl)
1 point
skryl
4 months ago
1 comment
206.
▲
Show HN: ReFlow Studio – An offline tool to dub, translate, and censor videos
(github.com/ananta-sj)
1 point
linearAmend
5 months ago
discuss
207.
▲
Auto-unloading models using __init_subclass__ (Python)
(github.com/Vrroom)
1 point
matroid
3 years ago
1 comment
208.
▲
Bookish: math-infested markdown to HTML and latex
(github.com/parrt)
1 point
ingve
8 years ago
discuss
209.
▲
Show HN: Mamba-Chat – A Chat LLM Based on State Space Models
(github.com/havenhq)
9 points
justusmattern
2 years ago
discuss
210.
▲
Ask HN: Which cloud provider offers AMD MI250/MI300?
2 points
fzysingularity
2 years ago
5 comments
More