ThiloteE
02e12089d3
Add Granite arch to model whitelist ( #3487 )
...
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2025-02-12 14:17:49 -05:00
Jared Van Bortel
22ebd42c32
Misc fixes for undefined behavior, crashes, and build failure ( #3465 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2025-02-06 11:22:52 -05:00
ThiloteE
6ef0bd518e
Whitelist OLMoE and Granite MoE ( #3449 )
...
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2025-02-04 18:00:07 -05:00
Jared Van Bortel
0c70b5a5f4
llamamodel: add missing softmax to fix temperature ( #3202 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-12-04 10:56:19 -05:00
Jared Van Bortel
225bf6be93
Remove binary state from high-level API and use Jinja templates ( #3147 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Co-authored-by: Adam Treat <treat.adam@gmail.com>
2024-11-25 10:04:17 -05:00
Jared Van Bortel
f07e2e63df
Use the token cache to infer greater n_past and reuse results ( #3073 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-10-31 11:19:12 -04:00
Jared Van Bortel
c3357b7625
Enable more warning flags, and fix more warnings ( #3065 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-10-18 12:11:03 -04:00
Jared Van Bortel
8e3108fe1f
Establish basic compiler warnings, and fix a few style issues ( #3039 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-10-09 09:11:50 -04:00
AT
ea1ade8668
Use different language for prompt size too large. ( #3004 )
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-09-27 12:29:22 -04:00
Jared Van Bortel
f9d6be8afb
backend: rebase llama.cpp on upstream as of Sep 26th ( #2998 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-09-27 12:05:59 -04:00
Jared Van Bortel
39005288c5
server: improve correctness of request parsing and responses ( #2929 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-09-09 10:48:57 -04:00
Jared Van Bortel
ca151f3519
repo: organize sources, headers, and deps into subdirectories ( #2917 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-27 17:22:40 -04:00
