Block a user
d4051c81ee
profiler: initial support for profiling graph ops
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
30caac3a68
llama : the WPM vocabs use the CLS token as BOS (#10930)
root
synced and deleted reference 2024-12-25 02:44:36 +00:00
refs/tags/refs/pull/10535/merge
at root/llama.cpp from mirror
root
synced and deleted reference 2024-12-25 02:44:36 +00:00
refs/tags/refs/pull/10967/merge
at root/llama.cpp from mirror
d4051c81ee
profiler: initial support for profiling graph ops
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
30caac3a68
llama : the WPM vocabs use the CLS token as BOS (#10930)
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
root
synced commits to refs/pull/10220/merge at root/llama.cpp from mirror
2024-12-25 02:44:36 +00:00
2ffcbb19ff
Merge
4ff0831ce6
into 9ba399dfa7
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
30caac3a68
llama : the WPM vocabs use the CLS token as BOS (#10930)
root
synced commits to refs/pull/10448/merge at root/llama.cpp from mirror
2024-12-25 02:44:36 +00:00
3e5e01a0ca
Merge
7c1a6853e5
into 9ba399dfa7
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10535/head at root/llama.cpp from mirror
2024-12-25 02:44:36 +00:00
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
30caac3a68
llama : the WPM vocabs use the CLS token as BOS (#10930)
60cfa728e2
ggml : use wstring for backend search paths (#10960)
root
synced commits to refs/pull/10573/merge at root/llama.cpp from mirror
2024-12-25 02:44:36 +00:00
fa2f378326
Merge
24bad77ebf
into 9ba399dfa7
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
30caac3a68
llama : the WPM vocabs use the CLS token as BOS (#10930)
root
synced commits to refs/pull/10663/merge at root/llama.cpp from mirror
2024-12-25 02:44:36 +00:00
cb4a2e8c9d
Merge
5293e17154
into 9ba399dfa7
9ba399dfa7
server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
root
synced commits to refs/pull/10742/merge at root/llama.cpp from mirror
2024-12-25 02:44:36 +00:00
d5f3254cc7
Merge
7006dd784c
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10851/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
d1448c1dff
Merge
5cb6209de5
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10873/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
73d1b8442d
Merge
a2d4b6fc81
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10894/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
21781db72d
Merge
fa522bc346
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10900/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
aafdf7b0c9
Merge
2116f48bec
into 09fe2e7613
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10902/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
e160b0608d
Merge
1e7e3384e1
into 09fe2e7613
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10912/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
66619e259b
Merge
d70f5fca74
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10928/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
572a2c50ab
Merge
59afb0160e
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)
root
synced commits to refs/pull/10940/head at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
b8679c0bb5
change to "response_fields"
4cf1fef320
clarify docs
root
synced commits to refs/pull/10942/merge at root/llama.cpp from mirror
2024-12-24 18:34:37 +00:00
02efc84343
Merge
e52a0f28e7
into 2cd43f4900
2cd43f4900
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
09fe2e7613
server: allow filtering llama server response fields (#10940)