OpenSource/ollama @ a2d33ee390c67a20ae9f24e805ea5199d8e609e7

Patrick Devine a2d33ee390 linter feeding		преди 7 месеца
..
ext_server	d632e23fba Add Windows arm64 support to official builds (#5712)	преди 7 месеца
generate	d632e23fba Add Windows arm64 support to official builds (#5712)	преди 7 месеца
llama.cpp @ 8962422b1c	5e2653f9fe llm: update llama.cpp commit to 8962422 (#6618)	преди 8 месеца
patches	504a410f02 llm: add solar pro (preview) (#6846)	преди 7 месеца
filetype.go	d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)	преди 11 месеца
ggla.go	6b252918fb update convert test to check result data	преди 9 месеца
ggml.go	bf612cd608 Merge pull request #6260 from ollama/mxyng/mem	преди 8 месеца
ggml_test.go	cb42e607c5 llm: speed up gguf decoding by a lot (#5246)	преди 10 месеца
gguf.go	6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128	преди 8 месеца
llm.go	d632e23fba Add Windows arm64 support to official builds (#5712)	преди 7 месеца
llm_darwin.go	cd5c8f6471 Optimize container images for startup (#6547)	преди 7 месеца
llm_linux.go	cd5c8f6471 Optimize container images for startup (#6547)	преди 7 месеца
llm_windows.go	dbba73469d runner: Set windows above normal priority (#6905)	преди 7 месеца
memory.go	56318fb365 Improve logging on GPU too small (#6666)	преди 8 месеца
memory_test.go	77903ab8b4 llama3.1	преди 8 месеца
server.go	a2d33ee390 linter feeding	преди 7 месеца
status.go	04210aa6dd Catch one more error log	преди 9 месеца