NVIDIA DCGM issues - Githubissues

NVIDIA / DCGM

NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs

Apache License 2.0

393 stars 50 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Fault injection in my pytorch training job

#192 hjx620 opened 3 weeks ago
1
Running separate DCGM on Kubernetes cluster

#191 ysk24ok opened 1 month ago
5
About dcgmError_enum 94 - DCGM_FR_EUD_NON_ZERO_EXIT_CODE. Anyone can told me what is reason to this case?

#190 Pig255 closed 3 weeks ago
3
DCGM 3.3.8

#189 dshaiknvidia closed 1 month ago
2
Prebuilt binaries in the source tree not compiled from source

#188 xnox opened 1 month ago
0
c++: add missing includes

#187 xnox opened 1 month ago
0
the issue of watching and querying metrics

#186 BetaZYN opened 1 month ago
0
dcgmi policy about Reset GPU Not effective

#185 mr-j-1992 opened 1 month ago
0
DCGM Policy Violation Notification channel reporting too many PCIe violations on P5 instance type from AWS EC2 (H100)

#184 haardm opened 2 months ago
1
H800 can not open profile feature? Help...

#183 cc8476 opened 2 months ago
1
Getting Utilization metrics

#182 apaz-cli opened 2 months ago
0
Support for Amazon Linux 2023 (AL2023)

#181 mbacchi opened 2 months ago
0
DCGM 3.3.7

#180 dshaiknvidia closed 2 months ago
0
Questions about enabling remote telemetry permissions

#179 MarcelFerrari opened 2 months ago
0
Add support for IPv6

#178 johnsushant opened 3 months ago
9
How to get current memory usage in bytes from dmon?

#177 johnsushant closed 3 months ago
1
Error: Health watches not enabled. Please enable watches

#176 corrtia opened 3 months ago
0
Cannot Retrieve GPU PIDs from DCGM Metrics

#175 doronkg opened 3 months ago
0
Hello, why /var/log/nv-hostengine.log file had many ERROR [5231:5273] [[NvSwitch]] ReadNvSwitchStatusAllSwitches()

#174 13416157913 opened 4 months ago
0
Cannot get "nvlink_flit_crc_error_count_total(409)" and "nvlink_data_crc_error_count_total(419)" in H800 System

#173 zdyang opened 4 months ago
2
DCGM 3.3.6

#172 dshaiknvidia closed 5 months ago
0
Incorrect values reported by dcgm stats

#171 MarcelFerrari closed 4 months ago
3
[Question] Amount of lag expected for metrics

#170 jaywonchung opened 5 months ago
2
[Question] Understanding multiplexing of profiling counters

#169 jaywonchung closed 5 months ago
2
Error setting up dcgm with startHostEngine mode from a golang based container

#168 haardm closed 5 months ago
1
Running diagnostics causes the Memory Usage of the other GPUs to increase

#167 BetaZYN opened 5 months ago
0
Facing unknown docker flag --compress while using build.sh

#166 premalathak12 opened 5 months ago
0
Facing error in running sdk_sample DCGMReader.py

#165 premalathak12 opened 5 months ago
2
Metrics around capturing gpu FLOPS

#164 krishh85 opened 5 months ago
4
Memory usage by dcgm during runtime diagnostics

#163 BetaZYN opened 5 months ago
2
a question about dcgm policy listening for xid

#162 BetaZYN opened 5 months ago
2
Removal of dependencies on cuda v10

#161 mamccorm closed 1 month ago
8
Build output does not include libnvperf_dcgm_host.so

#160 pintohutch closed 6 months ago
13
log spam of [[NvSwitch]] Not attached to NvSwitches. Aborting in cuda-dcgm-3.1.3.1 via Bright Cluster, RHEL 8

#159 SomePersonSomeWhereInTheWorld opened 6 months ago
8
dcgm dagnostic command exits with status 226

#158 rajeshvenkata opened 6 months ago
1
`power_usage` vs. `power_usage_instant`?

#157 jaywonchung closed 5 months ago
1
How to get SM Occupancy in real-time except dcgm in RTX Series?

#156 taekyounghan closed 6 months ago
1
dcgm-exporter crashes hostengine.

#155 krono opened 7 months ago
28
DCGM 3.3.5

#154 nikkon-dev closed 7 months ago
0
AppArmor profile for DCGM

#153 pintohutch opened 7 months ago
3
DCGM_FI_PROF_SM_ACTIVE is showing a value higher than 100% for MIG devices

#152 marceloamaral opened 8 months ago
5
Error setting watches. Result: The third-party Profiling module returned an unrecoverable error

#151 marceloamaral closed 8 months ago
4
DCGM cannot listen on ipv6 address

#150 Pingan2017 opened 8 months ago
0
No NVLINK activity on DGX-A100 320GB

#149 itzsimpl opened 8 months ago
6
diag --configfile option is silently ignored if --parameters options is present

#148 dmonakhov opened 8 months ago
0
DCGM 3.3.3

#147 nikkon-dev closed 8 months ago
0
Does DCGM supports creating groups of GPU from different hosts?

#146 deferen2 opened 9 months ago
1
Does DCGM support profiling metrics for A10 ?

#144 xuchenhui-5 opened 9 months ago
9
When I run diagnostics, the two GPUs in the group both get failed results.

#145 BetaZYN opened 9 months ago
2
common/DCGMStringHelpers: use memccpy for performance & error handling

#142 ecbadeaux opened 9 months ago
1