llama.cpp

Stay updated with the latest developments in Artificial Intelligence

Latest AI News

Source: llama.cpp

← Back to the latest stories

b11589: spec : remove tokens assert from dsv4 graph_mtp (#30444)
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 13, 20261 min read
b11582
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 13, 20261 min read
b11584
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 13, 20261 min read
b11581
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 13, 20262 min read
b11580
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 13, 20262 min read
b11577
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20261 min read
b11576
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20262 min read
b11575
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20262 min read
b11574
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20262 min read
b11572
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20261 min read
b11573: vulkan: pack FMA for f16 accumulation, no dot product op (#29877)
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20261 min read
b11571
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20261 min read
b11570
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20262 min read
b11569
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20263 min read
b11567
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20262 min read
b11568: examples : fix draft sampling and rejection handling (#30095)
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20261 min read
b11565
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 20261 min read
b11564
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cppOct 12, 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