auto-assign · Workflow runs · NVIDIA/TensorRT-LLM · GitHub

Actions

All workflows
Workflows
- Auto assign reviewers Auto assign reviewers
- auto-assign auto-assign
- Blossom-CI Blossom-CI
- Blossom-Status-Init Blossom-Status-Init
- Bot-Command Bot-Command
- Close inactive issues Close inactive issues
- CodeQL CodeQL
- Copilot code review Copilot code review
- Dependabot Updates Dependabot Updates
- L0-Test L0-Test
Management
- Caches
- Deployments

auto-assign

Actions

Loading...
Loading

auto-assign.yml

2,510 workflow runs

2,510 workflow runs

[Feature]: AutoDeploy: DeepSeek-R1 reference implementation auto-assign #2445: Issue #11112 labeled by lucaslie

1s

1s

[Feature]: AutoDeploy: MLA torch reference op and torch cached backend auto-assign #2444: Issue #11111 labeled by lucaslie

1s

1s

[Feature]: AutoDeploy: MLA revisited auto-assign #2443: Issue #11109 labeled by lucaslie

Skipped

Skipped

[AutoDeploy] Support silu+mul fusion auto-assign #2442: Issue #11094 labeled by galagam

1s

1s

[AutoDeploy] Support rope+attention fusion auto-assign #2441: Issue #11093 labeled by galagam

1s

1s

[Bug]: ImportError: cannot import name 'get_device' with transformers==4.57.1 (tensorrt-llm 1.3.0rc1 import fails) auto-assign #2440: Issue #11087 labeled by joonhyung-lee

1s

1s

[Feature]: AutoDeploy: Weight preloading for improving model loading time for AutoDeploy Backend auto-assign #2439: Issue #11086 labeled by taylor-yb-lee

1s

1s

[Usage]: Batching doesn't improve prefill throughput for llama 3.1 8B auto-assign #2438: Issue #11080 labeled by ShuaiShao93

1s

1s

[AutoDeploy Bug]: confused "No such file or directory" auto-assign #2437: Issue #11079 labeled by bobbych94

1s

1s

[Bug]: trtllm-bench failed with lora auto-assign #2436: Issue #11077 labeled by ShuaiShao93

1s

1s

[Feature]: Improved custom model registration auto-assign #2435: Issue #11071 labeled by govind-ramnarayan

2s

2s

[Feature]: AutoDeploy: mixed attention DP + MLP/MoE TP auto-assign #2434: Issue #11069 labeled by lucaslie

1s

1s

[Feature]: AutoDeploy: investigate+optimize comm collectives in TEP mode auto-assign #2433: Issue #11068 labeled by lucaslie

1s

1s

[Feature]: AutoDeploy: new load hook system auto-assign #2432: Issue #11067 labeled by lucaslie

1s

1s

[Question] tensorrt and tensorrtllm in the same image auto-assign #2431: Issue #11041 labeled by geraldstanje1

Skipped

Skipped

[Feature]: AutoDeploy: fake llm-models on cw-dfw auto-assign #2430: Issue #11038 labeled by lucaslie

1s

1s

[Feature]: dump current requests on failure or on SIGKILL auto-assign #2429: Issue #11036 labeled by okdimok

9s

9s

[Feature]: Migrate to Transformers v5 auto-assign #2428: Issue #11033 labeled by bmarimuthu-nv

1s

1s

[Feature]: Support GLM 4.7 Flash in AutoDeploy auto-assign #2427: Issue #11032 labeled by bmarimuthu-nv

1s

1s

[Performance]: Redundant Multi-modal Data Processing in Disagg-Deployment Increases TTFT auto-assign #2426: Issue #10632 labeled by karljang

1s

1s

[Bug]: No MTP support for Qwen3 Next auto-assign #2425: Issue #10313 labeled by karljang

2s

2s

[Bug]: Empty output issue from invalid channel establishment after parsing, for gpt-oss-120b. Often caused by garbage, repeated output tokens. auto-assign #2424: Issue #10614 labeled by karljang

2s

2s

[Bug]: transformers compatibility issues auto-assign #2423: Issue #10980 labeled by tcherckez-nvidia

1s

1s

[Bug]: transformers compatibility issues auto-assign #2422: Issue #10980 labeled by tcherckez-nvidia

1s

1s

[AutoDeploy][Bug]: Wrong test_tp_sharding config auto-assign #2421: Issue #10774 labeled by tcherckez-nvidia

1s

1s