mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-27 05:04:59 +00:00
Adding the following vLLM config options: disable_log_status, dtype, limit_mm_per_prompt
Signed-off-by: TheDropZone <brandonbeiler@gmail.com>
This commit is contained in:
parent
6424f0666d
commit
f0f2c87553
5 changed files with 64 additions and 23 deletions
|
@ -159,6 +159,12 @@ func grpcModelOpts(c config.BackendConfig) *pb.ModelOptions {
|
|||
SwapSpace: int32(c.SwapSpace),
|
||||
MaxModelLen: int32(c.MaxModelLen),
|
||||
TensorParallelSize: int32(c.TensorParallelSize),
|
||||
DisableLogStatus c.DisableLogStatus,
|
||||
DType: c.DType,
|
||||
// LimitMMPerPrompt vLLM
|
||||
LimitImagePerPrompt: int32(c.LimitMMPerPrompt.LimitImagePerPrompt),
|
||||
LimitVideoPerPrompt: int32(c.LimitMMPerPrompt.LimitVideoPerPrompt),
|
||||
LimitAudioPerPrompt: int32(c.LimitMMPerPrompt.LimitAudioPerPrompt),
|
||||
MMProj: c.MMProj,
|
||||
FlashAttention: c.FlashAttention,
|
||||
CacheTypeKey: c.CacheTypeK,
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue