mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 12:24:53 +00:00
More GPUs for more VRAM.
This commit is contained in:
parent
39620ce29f
commit
274b68ad7d
@ -13,7 +13,7 @@ def get_chicken():
|
|||||||
def flash_llava_next_handle(launcher):
|
def flash_llava_next_handle(launcher):
|
||||||
with launcher(
|
with launcher(
|
||||||
"llava-hf/llava-v1.6-mistral-7b-hf",
|
"llava-hf/llava-v1.6-mistral-7b-hf",
|
||||||
num_shard=2,
|
num_shard=4,
|
||||||
max_input_length=4000,
|
max_input_length=4000,
|
||||||
max_total_tokens=4096,
|
max_total_tokens=4096,
|
||||||
) as handle:
|
) as handle:
|
||||||
|
Loading…
Reference in New Issue
Block a user