Bump arctic-inference requirement (#28174)
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
@@ -48,7 +48,7 @@ buildkite-test-collector==0.1.9
|
|||||||
genai_perf==0.0.8
|
genai_perf==0.0.8
|
||||||
tritonclient==2.51.0
|
tritonclient==2.51.0
|
||||||
|
|
||||||
arctic-inference == 0.1.0 # Required for suffix decoding test
|
arctic-inference == 0.1.1 # Required for suffix decoding test
|
||||||
numba == 0.61.2 # Required for N-gram speculative decoding
|
numba == 0.61.2 # Required for N-gram speculative decoding
|
||||||
numpy
|
numpy
|
||||||
runai-model-streamer[s3,gcs]==0.15.0
|
runai-model-streamer[s3,gcs]==0.15.0
|
||||||
|
|||||||
@@ -40,7 +40,7 @@ anyio==4.6.2.post1
|
|||||||
# via
|
# via
|
||||||
# httpx
|
# httpx
|
||||||
# starlette
|
# starlette
|
||||||
arctic-inference==0.1.0
|
arctic-inference==0.1.1
|
||||||
# via -r requirements/test.in
|
# via -r requirements/test.in
|
||||||
argcomplete==3.5.1
|
argcomplete==3.5.1
|
||||||
# via datamodel-code-generator
|
# via datamodel-code-generator
|
||||||
|
|||||||
@@ -469,7 +469,7 @@ class SpeculativeConfig:
|
|||||||
if not has_arctic_inference():
|
if not has_arctic_inference():
|
||||||
raise ImportError(
|
raise ImportError(
|
||||||
"Arctic Inference is required for suffix decoding. "
|
"Arctic Inference is required for suffix decoding. "
|
||||||
"Install via `pip install arctic-inference==0.1.0`."
|
"Install via `pip install arctic-inference==0.1.1`."
|
||||||
)
|
)
|
||||||
if self.num_speculative_tokens is None:
|
if self.num_speculative_tokens is None:
|
||||||
# Suffix decoding decides the actual number of speculative tokens
|
# Suffix decoding decides the actual number of speculative tokens
|
||||||
|
|||||||
Reference in New Issue
Block a user