Crypto Flexs
  • DIRECTORY
  • CRYPTO
    • ETHEREUM
    • BITCOIN
    • ALTCOIN
  • BLOCKCHAIN
  • EXCHANGE
  • TRADING
  • HACKING
  • SLOT
  • CASINO
  • SUBMIT
Crypto Flexs
  • DIRECTORY
  • CRYPTO
    • ETHEREUM
    • BITCOIN
    • ALTCOIN
  • BLOCKCHAIN
  • EXCHANGE
  • TRADING
  • HACKING
  • SLOT
  • CASINO
  • SUBMIT
Crypto Flexs
Home»ADOPTION NEWS»AMD Launches AMD-135M: Innovation in Small Language Models
ADOPTION NEWS

AMD Launches AMD-135M: Innovation in Small Language Models

By Crypto FlexsSeptember 28, 20242 Mins Read
Facebook Twitter Pinterest LinkedIn Tumblr Email
AMD Launches AMD-135M: Innovation in Small Language Models
Share
Facebook Twitter LinkedIn Pinterest Email

Louisa Crawford
September 28, 2024 07:13

AMD unveiled the AMD-135M, the first compact language model with speculative decoding to improve AI model efficiency and performance.





In a significant advancement in artificial intelligence, AMD announced the release of AMD-135M, its first small language model (SLM). According to AMD.com, this new model aims to address some of the limitations faced by large language models (LLMs) such as GPT-4 and Llama while providing specialized functionality.

AMD-135M: The first AMD small language model

Part of the Llama family, the AMD-135M is AMD’s pioneering effort in SLM. The model was trained from scratch using the AMD Instinct™ MI250 accelerator and 670 billion tokens. The training process resulted in two different models: AMD-Llama-135M and AMD-Llama-135M-code. The former was pre-trained with regular data, while the latter was fine-tuned with an additional 20 billion tokens specifically for code data.

prior training: AMD-Llama-135M was trained for 6 days using 4 MI250 nodes. The AMD-Llama-135M code, a code-centric variant, required an additional four days for fine-tuning.

All associated training code, datasets, and model weights are open source, allowing developers to reproduce the model and contribute to the training of other SLMs and LLMs.

Optimization through speculative decoding

One notable advancement in AMD-135M is the use of speculative decoding. Existing autoregressive approaches for large-scale language models often have low memory access efficiency because each forward pass produces only a single token. Speculative decoding solves this problem by using a small draft model to generate candidate tokens and then verifying them with a larger target model. This method allows generating multiple tokens per forward pass, significantly improving memory access efficiency and inference speed.

Accelerate inference performance

AMD tested the performance of the AMD-Llama-135M code with a draft model of CodeLlama-7b on a variety of hardware configurations, including MI250 accelerators and Ryzen™ AI processors. The results show that inference performance is significantly improved when using speculative decoding. This enhancement establishes an end-to-end workflow for training and inference on selected AMD platforms.

next steps

AMD aims to foster innovation within the AI ​​community by providing open source reference implementations. The company encourages developers to explore and contribute to new areas of AI technology.

For more information about the AMD-135M, visit the full technology blog on AMD.com.

Image source: Shutterstock


Share. Facebook Twitter Pinterest LinkedIn Tumblr Email

Related Posts

Ether Lee (ETH) tests major support for $ 4,453 after the highest rejection.

August 31, 2025

Bitcoin analysts bet on $ 200K after hints of Fed.

August 23, 2025

‘Self -transactions, dressed in capital layout’: The cryptocurrency financial craze divides the industry.

August 15, 2025
Add A Comment

Comments are closed.

Recent Posts

GBC Mining Launches Scalable Cloud Mining Plans, Enabling Passive Income For Global Crypto Enthusiasts

September 6, 2025

The 320K holder of the WAVERS & Cardano Price Surges Surges BlockDag signals the next large encryption.

September 6, 2025

RLUSD Stablecoin is extended to Africa to supply power to the border between the border.

September 5, 2025

Bybit Establishes New B2B Unit To Drive Institutional Adoption Of Digital Assets

September 5, 2025

Lowkick Studio Launches $SHARDS Token On Top Tier Exchanges For WorldShards MMORPG

September 5, 2025

The cryptocurrency is falling when the tokens and stocks connected to Trump are under pressure.

September 5, 2025

Cango Inc. Reports Second Quarter 2025 Unaudited Financial Results

September 5, 2025

Coindesk July 2025 Report: Stablecoins and CBDC

September 5, 2025

NOWPayments To Participate In SiGMA Europe Rome 2025

September 4, 2025

Web3 Enabler Announces Blockchain Payments V3.1 At Northeast Dreamin In Boston

September 4, 2025

Is XRP The Dark Horse Of The Cryptocurrency World? Earn 652 XRP Daily Using Invro Mining’s Smart Contract

September 4, 2025

Crypto Flexs is a Professional Cryptocurrency News Platform. Here we will provide you only interesting content, which you will like very much. We’re dedicated to providing you the best of Cryptocurrency. We hope you enjoy our Cryptocurrency News as much as we enjoy offering them to you.

Contact Us : Partner(@)Cryptoflexs.com

Top Insights

GBC Mining Launches Scalable Cloud Mining Plans, Enabling Passive Income For Global Crypto Enthusiasts

September 6, 2025

The 320K holder of the WAVERS & Cardano Price Surges Surges BlockDag signals the next large encryption.

September 6, 2025

RLUSD Stablecoin is extended to Africa to supply power to the border between the border.

September 5, 2025
Most Popular

The merchant issues a bitcoin alarm and says that despite the BTC bounce, there is still a ‘fundamental weakness’. His goal is:

February 8, 2025

Bitwise Files for Spot Ethereum ETF Amid SEC Approval Uncertainty

March 28, 2024

The mechanism capital is leading the $ 4 million seed round to the Web3 Development Studio Mirai Labs.

February 11, 2025
  • Home
  • About Us
  • Contact Us
  • Disclaimer
  • Privacy Policy
  • Terms and Conditions
© 2025 Crypto Flexs

Type above and press Enter to search. Press Esc to cancel.