pull down to refresh

Meet PowerInfer: A Fast LLM on a Single Consumer-Grade GPUwww.marktechpost.com/2023/12/23/meet-powerinfer-a-fast-large-language-model-llm-on-a-single-consumer-grade-gpu-that-speeds-up-machine-learning-model-inference-by-11-times/
10 sats \ 2 comments \ @ch0k1 24 Dec 2023 AI
related
Nvidia Shows Off GPU for Ultra-Long Context Modelsdeveloper.nvidia.com/blog/nvidia-rubin-cpx-accelerates-inference-performance-and-efficiency-for-1m-token-context-workloads/
157 sats \ 1 comment \ @lunin 14 Sep AI
A New RISC-V Breakthrough Chip Merges CPU, GPU & AI into One - techovedastechovedas.com/a-new-risc-v-breakthrough-chip-merges-cpu-gpu-ai-into-one/
78 sats \ 0 comments \ @ch0k1 6 Apr 2024 tech
AMD unveils powerful new AI chip to challenge Nvidiaarstechnica.com/ai/2024/10/amd-unveils-powerful-new-ai-chip-to-challenge-nvidia/
41 sats \ 0 comments \ @ch0k1 11 Oct 2024 news
AMD Ryzen™ AI, the world's most powerful built-in AI processor in laptops!
31 sats \ 1 comment \ @ama 7 Jan tech
Hardware Acceleration of LLMs: A comprehensive survey and comparisonarxiv.org/abs/2409.03384
21 sats \ 0 comments \ @hn 7 Sep 2024 tech
1-Bit LLM: The Most Efficient LLM Possible?www.youtube.com/watch?v=7hMoz9q4zv0
533 sats \ 1 comment \ @carter 24 Jun AI
LLM in a Flash: Efficient LLM Inference with Limited Memoryhuggingface.co/papers/2312.11514
13 sats \ 1 comment \ @hn 20 Dec 2023 tech
Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLMwww.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm
306 sats \ 1 comment \ @nullama 13 Apr 2023 bitcoin
AMD's MI300X Outperforms Nvidia's H100 for LLM Inferencewww.blog.tensorwave.com/amds-mi300x-outperforms-nvidias-h100-for-llm-inference/
202 sats \ 0 comments \ @hn 13 Jun 2024 tech
LiveBench - A Challenging, Contamination-Free LLM Benchmarklivebench.ai
161 sats \ 0 comments \ @supratic 17 Jul AI
Apple collaborates with NVIDIA to research faster LLM performance - 9to5Mac9to5mac.com/2024/12/18/apple-collaborates-with-nvidia-to-research-faster-llm-performance/
14 sats \ 1 comment \ @Rsync25 19 Dec 2024 tech
Compiling LLMs into a MegaKernel: A path to low-latency inferencezhihaojia.medium.com/compiling-llms-into-a-megakernel-a-path-to-low-latency-inference-cf7840913c17
10 sats \ 0 comments \ @hn 19 Jun tech
Lm.rs: Minimal CPU LLM inference in Rust with no dependencygithub.com/samuel-vitorino/lm.rs
10 sats \ 0 comments \ @hn 11 Oct 2024 tech
NVIDIA: Transforming LLM Alignment with Efficient Reinforcement Learningwww.marktechpost.com/2024/05/05/nvidia-ai-open-sources-nemo-aligner-transforming-large-language-model-alignment-with-efficient-reinforcement-learning/
20 sats \ 0 comments \ @ch0k1 7 May 2024 tech
Bend: a high-level language that runs on GPUs (via HVM2)github.com/HigherOrderCO/Bend
51 sats \ 0 comments \ @hn 17 May 2024 tech
Don't Overthink It: A Survey of Efficient R1-style LRMsarxiv.org/abs/2508.02120
132 sats \ 2 comments \ @optimism 10 Aug AI
Gemma3 – The current strongest model that fits on a single GPUollama.com/library/gemma3
46 sats \ 0 comments \ @hn 12 Mar tech
LLaMA-Factory: Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)github.com/hiyouga/LLaMA-Factory
157 sats \ 0 comments \ @carter 19 Sep AI
Minimal implementation of Mamba, the new LLM architecture, in 1 file of PyTorchgithub.com/johnma2006/mamba-minimal
15 sats \ 1 comment \ @hn 20 Dec 2023 tech
DBRX: A new open LLMwww.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
10 sats \ 1 comment \ @hn 31 Mar 2024 tech
LLM evaluation at scale with the NeurIPS Efficiency Challengeblog.mozilla.ai/exploring-llm-evaluation-at-scale-with-the-neurips-large-language-model-efficiency-challenge/
110 sats \ 0 comments \ @localhost 22 Feb 2024 tech