tensorflow/serving
A flexible, high-performance serving system for machine learning models
C++Apache-2.0
Issues
- 0
- 4
Why TF Serving using one CUDA Compute Stream
#2221 opened by ndeep27 - 4
Add health check to Dockerfile
#2219 opened by alejones - 0
Ragged Tensor as an output from Tensorflow serving
#2222 opened by bajaj6 - 6
java.lang.RuntimeException: Unexpected code Response{protocol=http/1.1, code=400, message=Bad Request, url=http://localhost:8501/v1/models/myfruit:predict}
#2215 opened by x13872140520 - 7
OP_REQUIRES failed at xla_ops : UNIMPLEMENTED: Could not find compiler for platform CUDA: NOT_FOUND
#2214 opened by kmkolasinski - 7
Version 2.15 release?
#2204 opened by ustramooner - 0
ETA for TensorFlow Runtime Integration?
#2220 opened by jeongukjae - 4
OP_REQUIRES failed at xla_compile_on_demand_op.cc:290 : UNIMPLEMENTED: Could not find compiler for platform CUDA: NOT_FOUND
#2217 opened by rb-23 - 2
CUDA Graphs support for Tensorflow Serving
#2216 opened by ndeep27 - 3
Critical Vulnerability
#2206 opened by rook1337 - 4
Difference between Metrics emitted by TF Serving
#2208 opened by ndeep27 - 3
Who to contact for security issues
#2207 opened by psmoros - 1
Mismatch between TensorRT version used in TF 2.14 GPU docker images for tensorflow/serving and tensorflow/tensorflow causes segfault during inference
#2205 opened by saimidu - 3
Implement gRPC Server Reflection
#2148 opened by kylegallatin - 6
- 4
GPU inference in Docker container fails due to missing libdevice directory
#2201 opened by MartijnVanbiervliet - 4
Unable to compile prediction_service.proto for Golang
#2186 opened by 0110G - 3
TensorFlow serving seems to have no version attribute
#2194 opened by zhangggzh - 6
TF Serving batching for Sparse Tensors
#2188 opened by ndeepesh - 3
- 3
TF Serving gets stuck in the polling loop due to a non-existing model provided in config file
#2189 opened by yalcinaa - 6
TensorBoard profile showing high usage of relu
#2180 opened by law-lin - 1
Building tensorflow serving with TCMalloc
#2183 opened by jeongukjae - 13
Display full message in GRPC exception log
#2164 opened by Prabha-Veerubhotla - 2
Export `:tensorflow:serving:build_info` for prometheus
#2157 opened by jeongukjae - 4
Increased memory usage on TF 2.11
#2179 opened by ndeepesh - 3
Continuous batching
#2176 opened by sbhavani - 7
Memory usage of TensorFlow models
#2173 opened by ndeepesh - 9
Segmentation Fault in TF 2.11
#2171 opened by ndeepesh - 5
TF 2.11 on CUDA 11.8
#2169 opened by ndeepesh - 2
- 4
Failed to build Tensorflow serving Dockerfile(TF2.4.4)
#2167 opened by kbpark102 - 4
- 5
Monitor memory usage of TensorFlow models
#2156 opened by ndeepesh - 4
Failed to build TF serving from source
#2170 opened by nhatleSummer22 - 5
Expired GPG Key for Linux binary
#2165 opened by codekevinthumbtack - 4
When my model exceeds the maximum capacity of a single gpu, can I fragment the model to multiple gpu?
#2159 opened by for1314ai - 3
GPG Key expired: EXPKEYSIG 544B7F63BF9E4D5F Tensorflow Serving Developer (Tensorflow Serving APT repository key)
#2166 opened by la210 - 13
APIs for TF Serving Profiling
#2149 opened by ndeepesh - 2
File system scheme 'hdfs' not implemented
#2158 opened by KeithTt - 4
What's the match relationship between the docker `tensorflow/serving:xx-devel` and serving version?
#2153 opened by rhdong - 4
Couldn't build file external/org_tensorflow/tensorflow/core/util/version_info.cc
#2146 opened by dengguang2012 - 2
- 4
Memory increases due to hot deployment
#2142 opened by 749145134 - 7
GPU is slow than CPU
#2134 opened by yuxiazff - 3
- 2
- 2
Estimate memory usage of TensorFlow model
#2137 opened by ndeepesh - 5
2.12 release/docker image?
#2136 opened by dwyatte