llama.cpp

Stay updated with the latest developments in Artificial Intelligence

v0.7.0

LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.

llama.cppOct 15, 202611 min read

Agents on live hardware: reason where you must, engineer everywhere else

CoreWeave BlogOct 15, 202610 min read

b11669

llama.cppOct 15, 20261 min read

Latest AI News

Source: llama.cpp

b11662
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11658
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11655
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20262 min read
b11647
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11645
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11643
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11642
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11644: kv-cache: honor PARTIAL_ONLY in the plain KV cache (#30514)
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 15, 20261 min read
b11617
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11612
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20262 min read
b11618: HIP: use 64-row MMQ tiles for some quant types on RDNA3.5 (#28195)
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11614
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11613: vulkan: support mulmat bf16 activations (#29069)
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11610
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11609
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11608
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11607
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 14, 20261 min read
b11606
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 13, 20261 min read

Load more stories

AiByts Weekly Brief

Get the top AI news and tools straight to your inbox every week.

Weekly · AI news from llama.cpp

Join 15,000+ AI enthusiasts