| .. |
|
steps
|
3ea0d36000
Server: add tests for batch size, different seeds (#6950)
|
hai 1 ano |
|
embeddings.feature
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
hai 1 ano |
|
environment.py
|
bd60d82d0c
server tests : more pythonic process management; fix bare `except:` (#6146)
|
hai 1 ano |
|
issues.feature
|
9731134296
server: tests: passkey challenge / self-extend with context shift demo (#5832)
|
hai 1 ano |
|
parallel.feature
|
f482bb2e49
common: llama_load_model_from_url split support (#6192)
|
hai 1 ano |
|
passkey.feature
|
9731134296
server: tests: passkey challenge / self-extend with context shift demo (#5832)
|
hai 1 ano |
|
results.feature
|
3ea0d36000
Server: add tests for batch size, different seeds (#6950)
|
hai 1 ano |
|
security.feature
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
hai 1 ano |
|
server.feature
|
f482bb2e49
common: llama_load_model_from_url split support (#6192)
|
hai 1 ano |
|
slotsave.feature
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
hai 1 ano |
|
wrong_usages.feature
|
9731134296
server: tests: passkey challenge / self-extend with context shift demo (#5832)
|
hai 1 ano |
Johannes Gäßler
3ea0d36000
Server: add tests for batch size, different seeds (#6950)