issues Search Results · repo:vllm-project/aibrix language:"Jupyter Notebook"
Filter by
24 results
(92 ms)24 results
invllm-project/aibrix (press backspace or delete to remove)Can we remove the pkg/plugins/gateway/algorithms/util.go SelectRandomPodAsFallback instead of the current elegant way?
Originally posted by @Xunzhuo in https://github.com/vllm-project/aibrix/pull/1192#discussion_r2169317029 ...
kind/cleanup
zhangjyr
- Opened on Jul 1
- #1241
🐛 Describe the bug
When I run Llama-70B with AIBrix using Distributed KVCache and Cross-Engine KV Reuse, I get the following error:
llama3_3_70b_error_log.txt
This does not happen when I run a single-GPU ...
area/distributed
area/kv-cache
NirLevy98
- 4
- Opened on Jul 1
- #1240
🐛 Describe the bug
W0701 09:33:40.695920 1 util.go:88] environment variable AIBRIX_POD_RAYCLUSTERFLEET_LABEL is not set, using default value: orchestration.aibrix.ai/raycluster-fleet-name
I0701 ...
Jeffwan
- 1
- Opened on Jul 1
- #1238
🐛 Describe the bug
当在 配置例如benchmarks/scenarios/autoscaling/workload-configs/predefined/prompt-len-configs/HighFast.json JSON 中将 only_rise :
true 时，运行 benchmark.py 会触发以下错误：
TypeError: not supported between ...
area/autoscaling
area/benchmark
SmallHappyJerry
- 1
- Opened on Jun 27
- #1232
🐛 Describe the bug
When deploying KVCache with the Infinistore backend configured for RDMA (IB link), the kvcache-cluster-0 pod crashes on
startup with a segmentation fault. The failure occurs immediately ...
area/distributed
area/kv-cache
kind/bug
- 10
- Opened on Jun 24
- #1228
🚀 Feature Description and Motivation
Currently, the KVCache CRD in AIBrix supports node affinity through annotations such as
kvcache.orchestration.aibrix.ai/node-affinity-key and kvcache.orchestration.aibrix.ai/node-affinity-gpu-type. ...
area/distributed
area/kv-cache
kind/feature
triage/needs-information
- 7
- Opened on Jun 24
- #1227
🚀 Feature Description and Motivation
Summary
Currently, we deploy Envoy Gateway + Plugin(ext-proc) with a couple of configurations like EnvoyPatchPolicy,
EnvoyExtensionPolicy etc. Our vision is focus ...
area/gateway
kind/enhancement
priority/important-soon
Xunzhuo
- 3
- Opened on Jun 23
- #1225
🚀 Feature Description and Motivation
Add comprehensive unit and integration tests for the gateway server component, including request body handling, routing
logic, and error scenarios.
Use Case
Currently, ...
area/gateway
area/stability
ModiCodeCraftsman
- 2
- Opened on Jun 22
- #1216
🚀 Feature Description and Motivation
I use dify request the model, and the model occure the Run failed: [openai_api_compatible] Error: PluginInvokeError: {
args :{}, error_type : ChunkedEncodingError ...
area/gateway
kind/enhancement
triage/accepted
ying2025
- 3
- Opened on Jun 19
- #1207
🐛 Describe the bug
Image
Steps to Reproduce
job https://github.com/vllm-project/aibrix/actions/runs/15746092725?pr=1194
Expected behavior
it should pass
Environment
nightly
area/cicd
- 1
- Opened on Jun 19
- #1206
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.