Update dspark draft path in Inkling small cookbook (#34250)
This commit is contained in:
@@ -751,7 +751,7 @@ export const config = {
|
||||
"--tool-call-parser inkling",
|
||||
"--skip-server-warmup",
|
||||
"--speculative-algorithm DSPARK",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark",
|
||||
"--speculative-draft-model-quantization unquant",
|
||||
"--chunked-prefill-size 8192",
|
||||
"--cuda-graph-max-bs-prefill 8192",
|
||||
@@ -786,7 +786,7 @@ export const config = {
|
||||
"--tool-call-parser inkling",
|
||||
"--skip-server-warmup",
|
||||
"--speculative-algorithm DSPARK",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark",
|
||||
"--speculative-draft-model-quantization unquant",
|
||||
"--chunked-prefill-size 8192",
|
||||
"--cuda-graph-max-bs-prefill 8192",
|
||||
@@ -821,7 +821,7 @@ export const config = {
|
||||
"--tool-call-parser inkling",
|
||||
"--skip-server-warmup",
|
||||
"--speculative-algorithm DSPARK",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark",
|
||||
"--speculative-draft-model-quantization unquant",
|
||||
"--chunked-prefill-size 8192",
|
||||
"--cuda-graph-max-bs-prefill 8192",
|
||||
@@ -856,7 +856,7 @@ export const config = {
|
||||
"--tool-call-parser inkling",
|
||||
"--skip-server-warmup",
|
||||
"--speculative-algorithm DSPARK",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview",
|
||||
"--speculative-draft-model-path RadixArk/Inkling-Small-DSpark",
|
||||
"--speculative-draft-model-quantization unquant",
|
||||
"--chunked-prefill-size 8192",
|
||||
"--cuda-graph-max-bs-prefill 8192",
|
||||
|
||||
Reference in New Issue
Block a user