-
Notifications
You must be signed in to change notification settings - Fork 590
Pull requests: gpustack/gpustack
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(worker): clean up the download lock file on model file deletion
#5932
opened Jul 23, 2026 by
AmirF194
Loading…
[v2.3.0]feat: Support hiding specific backends or versions.
#5931
opened Jul 23, 2026 by
yxf0314
Contributor
Loading…
[v2.3.0]refactor: adopt replica-based launch for vLLM LB
#5922
opened Jul 21, 2026 by
yxf0314
Contributor
Loading…
feat(auth): add optional CAPTCHA protection for local login
#5907
opened Jul 20, 2026 by
shgef
Loading…
[v2.3.0]feat: add endpoint to download model instance logs files
#5786
opened Jul 6, 2026 by
yxf0314
Contributor
Loading…
add cookbook for Optimization model(sglang&vllm hot)
#5780
opened Jul 3, 2026 by
yiminghub2024
Contributor
Loading…
fix: enable host IPC for custom backend workloads
#5722
opened Jun 26, 2026 by
workcode-del
Loading…
fix(proxy): normalize output_text content in assistant messages for /v1/responses
#5503
opened Jun 6, 2026 by
xiaobao-k8s
Contributor
Loading…
8 of 9 tasks
fix: align vllm dependency version with model_registry sync source
#5490
opened Jun 5, 2026 by
xiaobao-k8s
Contributor
Loading…
3 of 4 tasks
feat: decouple users and enhance credentials
#5330
opened May 15, 2026 by
orangedeng
Contributor
•
Draft
feat: add gpustack info command for environment debugging
#5271
opened May 7, 2026 by
ifnodoraemon
Loading…
fix: validate_gpu_ids crash when gpu_selector lacks gpu_ids
#5269
opened May 7, 2026 by
jianzhichun
Loading…
3 tasks
feat(vllm): add --num-gpus parameter to ray start command
#5266
opened May 6, 2026 by
GitHub13555997029
Loading…
docs: add CONTRIBUTING.md with development guidelines
#5260
opened May 5, 2026 by
zichen0116
Loading…
fix: use actual GPU VRAM instead of tensor-split ratios for multi-GPU…
#5178
opened Apr 20, 2026 by
wlhj131
Loading…
Fix #5018: Failed to launch GPUStack worker with AWS EKS
#5075
opened Apr 2, 2026 by
JiwaniZakir
Loading…
perf: optimize worker inference backend cache init
#4791
opened Mar 5, 2026 by
yxf0314
Contributor
Loading…
feat: Load the list of models supported by each backend using YAML.
#4736
opened Mar 2, 2026 by
yxf0314
Contributor
Loading…
feat: add PATCH /v2/models/{id} for partial model updates
#4694
opened Feb 26, 2026 by
divnjl2
Loading…
5 tasks
feat: preserve worker identity across restarts to reconnect to existing models
#4633
opened Feb 15, 2026 by
diarworld
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-07-21.