Daniel Hiltgen 90ca84172c

Fix embeddings memory corruption (#6467) ...

* Fix embeddings memory corruption

The patch was leading to a buffer overrun corruption.  Once removed though, parallism
in server.cpp lead to hitting an assert due to slot/seq IDs being >= token count.  To
work around this, only use slot 0 for embeddings.

* Fix embed integration test assumption

The token eval count has changed with recent llama.cpp bumps (0.3.5+)

2024-08-22 14:51:42 -07:00

..

testdata/tools

server: collect nested tool call objects when parsing (#5824)

2024-07-22 12:38:03 -04:00

auth.go

fix nil deref in auth.go

2024-07-26 14:14:48 -07:00

download.go

server: reduce max connections used in download (#6347)

2024-08-13 16:47:35 -07:00

fixblobs_test.go

server: replace blob prefix separator from ':' to '-' (#3146)

2024-03-14 20:18:06 -07:00

fixblobs.go

server: replace blob prefix separator from ':' to '-' (#3146)

2024-03-14 20:18:06 -07:00

images.go

skip invalid manifest files

2024-08-14 16:55:45 -07:00

layer.go

fix: chmod new layer to 0o644 when creating it

2024-08-16 11:43:19 +08:00

manifest_test.go

lint

2024-08-01 17:06:06 -07:00

manifest.go

only skip invalid json manifests

2024-08-15 10:29:14 -07:00

model_test.go

cmd: speed up gguf creates (#6324)

2024-08-12 11:46:09 -07:00

model.go

cmd: speed up gguf creates (#6324)

2024-08-12 11:46:09 -07:00

modelpath_test.go

uint64

2024-07-22 11:49:02 -07:00

modelpath.go

models

2024-07-22 11:26:12 -07:00

prompt_test.go

lint

2024-08-01 17:06:06 -07:00

prompt.go

tools

2024-07-15 15:26:16 -07:00

routes_create_test.go

use testing tempdirs

2024-08-02 16:04:06 -07:00

routes_delete_test.go

manifest: Store layers inside manifests consistently as values.

2024-08-07 17:03:06 -07:00

routes_generate_test.go

comments

2024-07-31 15:58:55 -07:00

routes_list_test.go

lint

2024-08-01 17:06:06 -07:00

routes_test.go

Load Embedding Model on Empty Input (#6325)

2024-08-13 10:19:56 -07:00

routes.go

Load Embedding Model on Empty Input (#6325)

2024-08-13 10:19:56 -07:00

sched_test.go

llama3.1

2024-08-21 11:49:31 -07:00

sched.go

Fix embeddings memory corruption (#6467)

2024-08-22 14:51:42 -07:00

sparse_common.go

Don't hard fail on sparse setup error

2024-08-09 12:16:19 -07:00

sparse_windows.go

Don't hard fail on sparse setup error

2024-08-09 12:16:19 -07:00

upload.go

server: limit upload parts to 16 (#6411)

2024-08-19 09:20:52 -07:00