Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

auto-assign

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-assign.yml
1,047 workflow run results
1,047 workflow run results

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[Usage]: how to deploy Qwen2.5-VL-7B-Instruct with triton-server auto-assign #1902: Issue #9142 labeled by lqq-feel
6s
6s
[Feature][AutoDeploy]: Factory sharding as default auto-assign #1901: Issue #9137 labeled by greg-kwasniewski1
1s
1s
[Feature][AutoDeploy]: MIxed EP+TP sharding auto-assign #1900: Issue #9136 labeled by greg-kwasniewski1
1s
1s
speculative decoding in gemma3 auto-assign #1899: Issue #6067 labeled by karljang
1s
1s
[Feature]: KVCacheManager dump/load support auto-assign #1898: Issue #6962 labeled by karljang
1s
1s
[Feature]: Add support for AFD in Step3 paper auto-assign #1897: Issue #7253 labeled by karljang
1s
1s
[Feature]: Add all models to the AD dashboard auto-assign #1896: Issue #7399 labeled by karljang
7s
7s
Function tooling like in vllm auto-assign #1895: Issue #6154 labeled by karljang
1s
1s
[Feature]: AutoDeploy: Enable fp8 kv cache for Nano-v3 fp8 model auto-assign #1894: Issue #9102 labeled by suyoggupta
1s
1s
[Bug]: AutoModelForCausalLM. auto-assign #1893: Issue #8942 labeled by karljang
1s
1s
[Feature]: Support for _ and - parsing of CLI arguments in build_and_run_ad auto-assign #1892: Issue #9100 labeled by greg-kwasniewski1
1s
1s
[Feature]: Sharding support for latent MoE auto-assign #1891: Issue #9098 labeled by greg-kwasniewski1
2s
2s
[Bug]: Output includes tokens from other prompts when host kv cache enabled auto-assign #1890: Issue #8813 labeled by karljang
2s
2s
[Feature][AutoDeploy] AOT compile moe_align kernel auto-assign #1889: Issue #9082 labeled by pcastonguay
8s
8s
[Feature]: Add an option to configure the fused MoE backend from config YAML auto-assign #1887: Issue #9096 labeled by nzmora-nvidia
1s
1s
[Feature]: Add an option to configure the fused MoE backend from config YAML auto-assign #1888: Issue #9096 labeled by nzmora-nvidia
1s
1s
[Bug]: Tensor parallelism on A40 results in CUDA illegal instruction error auto-assign #1886: Issue #9086 labeled by AlessioNetti
1s
1s
Crash During Stress Testing with Release v0.19.0rc0 auto-assign #1885: Issue #3736 labeled by karljang
Skipped
Skipped
Incompatibility between dp_attention and enable_chunked_prefill causes service hang on exceeding max_num_tokens auto-assign #1884: Issue #5267 labeled by karljang
1s
1s
[Feature][AutoDeploy] AOT compile moe_align kernel auto-assign #1883: Issue #9082 labeled by suyoggupta
8s
8s
How to enable deepep(especially cuda graph in generation) in PD disaggrated serving auto-assign #1882: Issue #5869 labeled by karljang
1s
1s
Context node crash when using PD Disaggregation auto-assign #1881: Issue #3937 labeled by karljang
1s
1s
The program freezes/hangs when using kv_cache_config=KvCacheConfig(event_buffer_max_size), batched_logits_processor=MyBatchedLogitsProcessor. auto-assign #1880: Issue #3857 labeled by karljang
1s
1s
[Bug]: function cbapi->getCuptiStatus() failed with error CUPTI_ERROR_MULTIPLE_SUBSCRIBERS_NOT_SUPPORTED auto-assign #1879: Issue #9073 labeled by zejunchen-zejun
1s
1s
Support for Qwen2-VL 2B/4B? or Qwen2.5-VL auto-assign #1878: Issue #8927 labeled by yechank-nvidia
1s
1s