Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

Bot-Command

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
bot-command.yml
79,350 workflow run results
79,350 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Unable to profile cpp benchmark due to NCCL error Bot-Command #79239: Issue comment #2448 (comment) created by karljang
1s
1s
Build Qwen2-72B-Instruct model by INT4-AWQ quantization failed Bot-Command #79238: Issue comment #2445 (comment) created by karljang
1s
1s
tensorrtllm backend fails when kv cache is disabled Bot-Command #79237: Issue comment #2443 (comment) created by karljang
1s
1s
Inference RoBERTa on Triton server using TRT_LLM Bot-Command #79236: Issue comment #2440 (comment) created by karljang
Skipped
Skipped
[TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 1). Bot-Command #79235: Issue comment #8194 (comment) created by tensorrt-cicd
1s
1s
[bug] unnecessary batch logits post processor calls Bot-Command #79234: Issue comment #2439 (comment) created by karljang
1s
1s
[TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 1). Bot-Command #79233: Issue comment #8194 (comment) created by zheyuf
1s
1s
FA V2 Nonusage during Decode/Generation Phase Bot-Command #79232: Issue comment #2438 (comment) created by karljang
1s
1s
Error in data types: using model with lora Bot-Command #79231: Issue comment #2434 (comment) created by karljang
1s
1s
trtllm-build ignores --model_cls_file and --model_cls_name Bot-Command #79230: Issue comment #2430 (comment) created by karljang
1s
1s
trt_build for Llama 3.1 70B fp8 fails with CUDA error Bot-Command #79229: Issue comment #2429 (comment) created by karljang
1s
1s
trt_build for Llama 3.1 70B w4a8 fails with CUDA error Bot-Command #79228: Issue comment #2428 (comment) created by karljang
1s
1s
why Dit does not support pp_size > 1 Bot-Command #79227: Issue comment #2427 (comment) created by karljang
1s
1s
[None][perf] Adjust select_alltoall_method_type. Bot-Command #79226: Issue comment #8950 (comment) created by tensorrt-cicd
1s
1s
[None][chore] Refactor KV Connector Implementation Bot-Command #79225: Issue comment #9186 (comment) created by tensorrt-cicd
Skipped
Skipped
[None][chore] Refactor KV Connector Implementation Bot-Command #79224: Issue comment #9186 (comment) created by jthomson04
1s
1s
[TRTINFRA-7280][infra] Support enroot/pyxis clusters in multi-node SLURM and enable oci-hsg GB200 in post-merge Bot-Command #79223: Issue comment #9117 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-9247][infra] Upgrade NIXL to 0.7.1 Bot-Command #79222: Issue comment #9055 (comment) created by tensorrt-cicd
Skipped
Skipped
[https://nvbugs/5582133][fix] Fix protocol violation in AgentConnectionManager Bot-Command #79221: Issue comment #8764 (comment) created by schetlur-nv
1s
1s
[None] [fix] Fix missing ActivationType issue Bot-Command #79220: Issue comment #9171 (comment) created by nzmora-nvidia
1s
1s
[TRTINFRA-7280][infra] Support enroot/pyxis clusters in multi-node SLURM and enable oci-hsg GB200 in post-merge Bot-Command #79219: Issue comment #9117 (comment) created by tensorrt-cicd
1s
1s
[TRTINFRA-7280][infra] Support enroot/pyxis clusters in multi-node SLURM and enable oci-hsg GB200 in post-merge Bot-Command #79218: Issue comment #9117 (comment) created by mlefeb01
Skipped
Skipped
[TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 1). Bot-Command #79217: Issue comment #8194 (comment) created by tensorrt-cicd
1s
1s
[None][chore] Refactor KV Connector Implementation Bot-Command #79216: Issue comment #9186 (comment) created by jthomson04
1s
1s
[https://nvbugs/5481198][fix] Enable DeepseekR1 cases on devices with enough memory Bot-Command #79215: Issue comment #9125 (comment) created by tensorrt-cicd
Skipped
Skipped