home
home
๐Ÿ’ป

Hands-on

Hands-on
Search
CUDA C ์ˆ˜์ค€์—์„œ ํ•œ๊ตญ์–ด ํ† ํฌ๋‚˜์ด์ € ๊ตฌํ˜„
ํ•œ๊ตญ์–ด ํ† ํฌ๋‚˜์ด์ € ์ฒ˜๋ฆฌ
๊ณ ์„ํ˜„ / CEO
OOV
CUDA
tokenizer
Encoding
์ง€๊ทนํžˆ ์‚ฌ์ ์ธ ๋‚˜๋งŒ์˜ LLM, ๊ฐ€์งˆ ์ˆ˜ ์žˆ์„๊นŒ? [2ํŽธ - WebGPU Build & Run]
๊ฐœ์ธ์˜ ์“ฐ์ž„์— ๋งž์ถ˜ ์ดˆ๊ฑฐ๋Œ€ ์–ธ์–ด ๋ชจ๋ธ ํ™œ์šฉ
๊น€๋•ํ˜„ / Head of Development
LLM
Generation
WebAssembly
WebGPU
Vector Database ๊ตฌ์ถ• ์‹ค์Šต
Vector Database ๊ตฌ์ถ• ์‹ค์Šต
์†ก๋ช…ํ•˜ / MLOps Engineer
Vector Database
NLP
์ง€๊ทนํžˆ ์‚ฌ์ ์ธ ๋‚˜๋งŒ์˜ LLM, ๊ฐ€์งˆ ์ˆ˜ ์žˆ์„๊นŒ? [1ํŽธ - ํŒŒ์ธํŠœ๋‹]
์ดˆ๊ฑฐ๋Œ€ ์–ธ์–ด๋ชจ๋ธ์— ํ•™์Šต์‹œํ‚จ ๋‚ด ๋ฐ์ดํ„ฐ๋กœ ๋‚˜์—๊ฒŒ ์ตœ์ ํ™”๋œ ์ผ์„ ์‹œ๋„ํ•ด๋ณด์ž.
๋ฐ•์ง„ํ˜• (Sigrid Jin) / Software Engineer
Finetuning
Llama
LLM
WebGPU๋ฅผ ํ†ตํ•œ private ์ƒ์„ฑ AI์˜ Hybrid Inference
WebGPU๋ฅผ ํ†ตํ•œ ๊ฐœ์ธํ™” ์ƒ์„ฑ ์ธ๊ณต์ง€๋Šฅ์˜ ์ถ”๋ก  ๋ฐฉ๋ฒ•๋ก  ์†Œ๊ฐœ
๊ณ ์„ํ˜„ / CEO
WebGPU
AI
Hybrid Inference
Paper Review
Data Curation
Hands-on
Development Glossary
Company