Daniel Hiltgen 1f50356e8e Bump ROCm on windows to 6.1.2 ...

This also adjusts our algorithm to favor our bundled ROCm.
I've confirmed VRAM reporting still doesn't work properly so we
can't yet enable concurrency by default.

2024-07-10 11:01:22 -07:00

..

ext_server

llm: allow gemma 2 to context shift (#5534)

2024-07-07 13:41:51 -04:00

generate

Bump ROCm on windows to 6.1.2

2024-07-10 11:01:22 -07:00

llama.cpp @ a8db2a9ce6

Update llama.cpp submodule to a8db2a9c (#5530)

2024-07-07 13:03:09 -04:00

patches

Update llama.cpp submodule to a8db2a9c (#5530)

2024-07-07 13:03:09 -04:00

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

llm: speed up gguf decoding by a lot (#5246)

2024-06-24 21:47:52 -07:00

ggml_test.go

llm: speed up gguf decoding by a lot (#5246)

2024-06-24 21:47:52 -07:00

ggml.go

gemma2 graph

2024-06-27 13:34:52 -07:00

gguf.go

llm: speed up gguf decoding by a lot (#5246)

2024-06-24 21:47:52 -07:00

llm_darwin_amd64.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_darwin_arm64.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_linux.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_windows.go

Move nested payloads to installer and zip file on windows

2024-04-23 16:14:47 -07:00

llm.go

Statically link c++ and thread lib

2024-07-09 11:34:30 -07:00

memory_test.go

llm: speed up gguf decoding by a lot (#5246)

2024-06-24 21:47:52 -07:00

memory.go

handle asymmetric embedding KVs

2024-06-20 09:57:27 -07:00

payload.go

Fix corner cases on tmp cleaner on mac

2024-07-03 13:10:14 -07:00

server.go

Merge pull request #5126 from ollama/mxyng/messages

2024-07-09 09:20:44 -07:00

status.go

fix error detection by limiting model loading error parsing (#5472)

2024-07-03 20:04:30 -04:00