llama-node

What's Changed

• feat: implement chat feature to rwkv by @yorkzero831 in https://github.com/Atome-FE/llama-node/pull/63
• feat: update cuda dynamic compiling by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/66
• feature: optimiza llama.cpp loading, fix llama.cpp tokenizer, unify logger by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/75
• update: refractor onnx by @hlhr2...

What's Changed

• update: sync latest llama.cpp branch by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/61
• feat: upgrade llama-rs to llm by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/62

Full Changelog: https://github.com/Atome-FE/llama-node/compare/v0.1.1...v0.1.4

What's Changed

• feat: impl abortable inference by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/58

Full Changelog: https://github.com/Atome-FE/llama-node/compare/v0.1.0...v0.1.1

What's Changed

• feature: impl naive gpt2 by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/51
• feature: implemented parallel inference for llama-rs, implemented naive sequential async inference for llama-cpp and rwkv-cpp by @hlhr202 in https://github.com/Atome-FE/llama-node/pull/52

Full Changelog: https://github.com/Atome-FE/llama-node/compare/v0.0.37...v0.1.0

What's Changed

• fix: utf8 encode issue by @yorkzero831 in https://github.com/Atome-FE/llama-node/pull/49

Full Changelog: https://github.com/Atome-FE/llama-node/compare/v0.0.36...v0.0.37