Daniel Hiltgen c3d321d405 llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174) ... This workaround logic in llama.cpp is causing crashes for users with less system memory than VRAM.		2024-10-12 09:56:49 -07:00
..
ext_server	Re-introduce the llama package (#5034)	2024-10-08 08:53:54 -07:00
generate	llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174)	2024-10-12 09:56:49 -07:00
llama.cpp@8962422b1c	llm: update llama.cpp commit to 8962422 (#6618)	2024-09-03 21:12:39 -04:00
patches	llm: add solar pro (preview) (#6846)	2024-09-17 18:11:26 -07:00
filetype.go	Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)	2024-05-23 13:21:49 -07:00
ggla.go	update convert test to check result data	2024-07-31 10:59:38 -07:00
ggml.go	Merge pull request #6260 from ollama/mxyng/mem	2024-09-05 13:22:08 -07:00
ggml_test.go	llm: speed up gguf decoding by a lot (#5246)	2024-06-24 21:47:52 -07:00
gguf.go	add conversion for microsoft phi 3 mini/medium 4k, 128	2024-08-12 15:13:29 -07:00
llm_darwin.go	Optimize container images for startup (#6547)	2024-09-12 12:10:30 -07:00
llm_linux.go	Optimize container images for startup (#6547)	2024-09-12 12:10:30 -07:00
llm_windows.go	runner: Set windows above normal priority (#6905)	2024-09-21 16:54:49 -07:00
memory.go	Improve logging on GPU too small (#6666)	2024-09-06 08:29:36 -07:00
memory_test.go	llama3.1	2024-08-21 11:49:31 -07:00
server.go	server: Don't clear cmd when closing a server	2024-10-09 20:39:04 -07:00
status.go	Catch one more error log	2024-08-05 09:28:07 -07:00