Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

auto-assign

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-assign.yml
1,555 workflow run results
1,555 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Feature]: Add support for guided decoding in AutoDeploy auto-assign #1663: Issue #8245 labeled by suyoggupta
1s
1s
[Feature]: Add support for tool calling in AutoDeploy. auto-assign #1662: Issue #8244 labeled by suyoggupta
1s
1s
[Bug]: PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True causes crash during startup if enable_attention_dp:false auto-assign #1661: Issue #8243 labeled by josephrocca
1s
1s
[Feature]: Add AutoGPTQ support for AutoDeploy auto-assign #1660: Issue #8242 labeled by Fridah-nv
1s
1s
enableBlockReuse is available for multimodal ? auto-assign #1659: Issue #2459 labeled by karljang
2s
2s
[AutoDeploy]: Multi-stream optimizations for DS-R1 auto-assign #1658: Issue #8238 labeled by nzmora-nvidia
5m 33s
5m 33s
[AutoDeploy]: multi token prediction (MTP) for DS-R1 auto-assign #1657: Issue #8237 labeled by nzmora-nvidia
1m 53s
1m 53s
[AutoDeploy]: W4A8 for DS-R1 auto-assign #1656: Issue #8236 labeled by nzmora-nvidia
5m 29s
5m 29s
[AutoDeploy]: Faster model compilation for DS-R1 auto-assign #1655: Issue #8239 labeled by nzmora-nvidia
1m 0s
1m 0s
[AutoDeploy]: add to trtllm-bench loading of partial model when using manual pytorch auto-assign #1654: Issue #8241 labeled by nzmora-nvidia
1m 13s
1m 13s
[AutDeploy]: Faster weights loading for DS-R1 auto-assign #1653: Issue #8240 labeled by nzmora-nvidia
42s
42s
[AutoDeploy]: NVFP4 for DS-R1 auto-assign #1652: Issue #8235 labeled by nzmora-nvidia
10m 30s
10m 30s
[Feature]: FP8 for DS-R1 auto-assign #1651: Issue #8234 labeled by nzmora-nvidia
1m 17s
1m 17s
[AutoDeploy]: MLA optimizations for DS-R1 auto-assign #1650: Issue #8233 labeled by nzmora-nvidia
2m 32s
2m 32s
[AutoDeploy]: Improve MoE performance for TP>1 auto-assign #1649: Issue #8232 labeled by nzmora-nvidia
2m 48s
2m 48s
[Usage]: I want to change the default engine from PyTorch to TRT-LLM in TensorRT-LLM v1.0.0 auto-assign #1648: Issue #8223 labeled by ASH29033
1s
1s
[Bug]: EXAONE 4.0 FP8 trtllm-serve failure auto-assign #1647: Issue #8221 labeled by lkm2835
2s
2s
[Bug]: self.executor_request_queue.get_canceled_req_ids_size() grows unboundedly unless enable_attention_dp:true is set auto-assign #1646: Issue #8131 labeled by karljang
1s
1s
[Bug]: Deepseek V3 FP4 LWS PD Crash on B200 on Long Prompt auto-assign #1645: Issue #8205 labeled by bryangopal
1s
1s
[Bug]: Deepseek V3 FP4 LWS PD Crash on B200 during KV Transfer auto-assign #1644: Issue #8204 labeled by bryangopal
1s
1s
[Feature][AutoDeploy] TP sharding of Mamba layers auto-assign #1643: Issue #8201 labeled by suyoggupta
Skipped
Skipped
[Bug]: response_format Parameter Not Properly Handled in Chat Completions auto-assign #1642: Issue #8196 labeled by 0xd8b
1s
1s
[AutoDeploy][Feature]: Setup the new servers to run the AD dashboard auto-assign #1640: Issue #8184 labeled by nvchenghaoz
1s
1s
[AutoDeploy][Feature]: Setup the new servers to run the AD dashboard auto-assign #1641: Issue #8184 labeled by nvchenghaoz
1s
1s
[Bug]: gpt-oss-120 tinygemm2_cuda.cu 64 - invalid argument auto-assign #1639: Issue #8179 labeled by voipmonitor
1s
1s