Georgi GerganovandGitHub faf69d4237 llama : sanitize invalid tokens (#9357) ...

* common : do not add null tokens during warmup

ggml-ci

* llama : check that the input tokens are valid

ggml-ci

* tests : fix batch size of bert model

ggml-ci

2024-09-08 00:33:13 +03:00

..

steps

server : simplify state machine for slot (#9283)

2024-09-06 23:21:29 +02:00

embeddings.feature

llama : sanitize invalid tokens (#9357)

2024-09-08 00:33:13 +03:00

environment.py

server tests : more pythonic process management; fix bare except: (#6146)

2024-03-20 06:33:49 +01:00

issues.feature

server: tests: passkey challenge / self-extend with context shift demo (#5832)

2024-03-02 22:00:14 +01:00

lora.feature

server : add lora hotswap endpoint (WIP) (#8857)

2024-08-06 17:33:39 +02:00

parallel.feature

server : simplify state machine for slot (#9283)

2024-09-06 23:21:29 +02:00

passkey.feature

server : simplify state machine for slot (#9283)

2024-09-06 23:21:29 +02:00

results.feature

server : fix temperature + disable some tests (#7409)

2024-05-20 22:10:03 +10:00

security.feature

json-schema-to-grammar improvements (+ added to server) (#5978)

2024-03-21 11:50:43 +00:00

server.feature

json: fix additionalProperties, allow space after enum/const (#7840)

2024-06-26 01:45:58 +01:00

slotsave.feature

Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)

2024-05-21 14:39:48 +02:00

wrong_usages.feature

server : refactor multitask handling (#9274)

2024-09-02 17:11:51 +02:00