| .. |
|
ext_server
|
15c2d8fe14
server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)
|
9 ヶ月 前 |
|
generate
|
283948c83b
Adjust windows ROCm discovery
|
10 ヶ月 前 |
|
llama.cpp @ 1e6f6554aa
|
e04c7012c2
update llama.cpp submodule to `1e6f6554` (#6208)
|
9 ヶ月 前 |
|
patches
|
e04c7012c2
update llama.cpp submodule to `1e6f6554` (#6208)
|
9 ヶ月 前 |
|
filetype.go
|
d6f692ad1a
Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)
|
1 年間 前 |
|
ggla.go
|
6b252918fb
update convert test to check result data
|
9 ヶ月 前 |
|
ggml.go
|
6ffb5cb017
add conversion for microsoft phi 3 mini/medium 4k, 128
|
9 ヶ月 前 |
|
ggml_test.go
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
11 ヶ月 前 |
|
gguf.go
|
6ffb5cb017
add conversion for microsoft phi 3 mini/medium 4k, 128
|
9 ヶ月 前 |
|
llm.go
|
b732beba6a
lint
|
9 ヶ月 前 |
|
llm_darwin_amd64.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
10 ヶ月 前 |
|
llm_darwin_arm64.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
10 ヶ月 前 |
|
llm_linux.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
10 ヶ月 前 |
|
llm_windows.go
|
e12fff8810
Enable windows error dialog for subprocess startup
|
10 ヶ月 前 |
|
memory.go
|
8e0641a9bf
handle asymmetric embedding KVs
|
11 ヶ月 前 |
|
memory_test.go
|
b732beba6a
lint
|
9 ヶ月 前 |
|
payload.go
|
0e982bc1f4
Fix corner cases on tmp cleaner on mac
|
10 ヶ月 前 |
|
server.go
|
15c2d8fe14
server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)
|
9 ヶ月 前 |
|
status.go
|
04210aa6dd
Catch one more error log
|
9 ヶ月 前 |
Michael Yang
6ffb5cb017
add conversion for microsoft phi 3 mini/medium 4k, 128