Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

auto-assign

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-assign.yml
140 workflow runs
140 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support for LLaMa3.3 auto-assign #43: Issue #2567 labeled by nv-guomingz
December 18, 2024 02:04 2s
December 18, 2024 02:04 2s
Which version of InternVL does TensorRT-llm 1.5 support ? auto-assign #42: Issue #2578 labeled by nv-guomingz
December 18, 2024 01:57 2s
December 18, 2024 01:57 2s
OOM when building engine for meta-llama/Llama-3.1-405B-FP8 on 8 x A100 80G auto-assign #41: Issue #2586 labeled by nv-guomingz
December 18, 2024 01:33 3s
December 18, 2024 01:33 3s
llava-onevision convert bug auto-assign #40: Issue #2585 labeled by nv-guomingz
December 18, 2024 01:32 49s
December 18, 2024 01:32 49s
llava-onevision convert bug auto-assign #39: Issue #2585 labeled by liyi-xia
December 17, 2024 10:20 2s
December 17, 2024 10:20 2s
trtllm-build ignores --model_cls_file and --model_cls_name auto-assign #38: Issue #2430 labeled by nv-guomingz
December 17, 2024 10:04 42s
December 17, 2024 10:04 42s
[feature request] lm_head quantization auto-assign #37: Issue #2550 labeled by nv-guomingz
December 17, 2024 09:55 41s
December 17, 2024 09:55 41s
Performance issue with long context auto-assign #36: Issue #2548 labeled by nv-guomingz
December 17, 2024 09:46 50s
December 17, 2024 09:46 50s
LayerInfo doesn't support fp8 and int4_awq dtype? auto-assign #35: Issue #2547 labeled by nv-guomingz
December 17, 2024 09:45 41s
December 17, 2024 09:45 41s
int8 slower than bf16 on A100 auto-assign #34: Issue #2553 labeled by nv-guomingz
December 17, 2024 02:13 40s
December 17, 2024 02:13 40s
int8 slower than bf16 on A100 auto-assign #33: Issue #2553 labeled by nv-guomingz
December 17, 2024 02:11 39s
December 17, 2024 02:11 39s
trtllm-bench missing support of moe_ep_size / moe_tp_size. auto-assign #32: Issue #2577 labeled by juewAtAmazon
December 16, 2024 01:59 2s
December 16, 2024 01:59 2s
Testing Actions auto-assign #31: Issue #2572 labeled by kevinch-nv
December 12, 2024 21:34 2s
December 12, 2024 21:34 2s
Testing Actions auto-assign #30: Issue #2572 labeled by kevinch-nv
December 12, 2024 21:34 38s
December 12, 2024 21:34 38s
TRT-LLM fails on GH200 node auto-assign #29: Issue #2571 labeled by ttim
December 12, 2024 21:26 2s
December 12, 2024 21:26 2s
What does "weights_scaling_factor_2" mean in safetensor results of awq_w4a8 auto-assign #28: Issue #2561 labeled by nv-guomingz
December 12, 2024 00:14 40s
December 12, 2024 00:14 40s
What does "weights_scaling_factor_2" mean in safetensor results of awq_w4a8 auto-assign #27: Issue #2561 labeled by nv-guomingz
December 12, 2024 00:08 42s
December 12, 2024 00:08 42s
What does "weights_scaling_factor_2" mean in safetensor results of awq_w4a8 auto-assign #26: Issue #2561 labeled by nv-guomingz
December 12, 2024 00:07 50s
December 12, 2024 00:07 50s
Build fails on w8a8 with kv_cache_dtype FP8 auto-assign #25: Issue #2559 labeled by darraghdog
December 10, 2024 17:05 3s
December 10, 2024 17:05 3s
Can TensorRT-LLM Handle High Levels of Concurrent Requests? auto-assign #24: Issue #2514 labeled by hello-11
December 10, 2024 08:52 3s
December 10, 2024 08:52 3s
Can TensorRT-LLM Handle High Levels of Concurrent Requests? auto-assign #23: Issue #2514 labeled by hello-11
December 10, 2024 08:52 43s
December 10, 2024 08:52 43s
Medusa performance degrades with batch size larger than 1 auto-assign #22: Issue #2482 labeled by hello-11
December 10, 2024 06:57 3s
December 10, 2024 06:57 3s
Can't build whisper engines with past two releases auto-assign #21: Issue #2508 labeled by hello-11
December 10, 2024 06:49 3s
December 10, 2024 06:49 3s
qserve is slower then awq int4 for llama2-7b on H100 auto-assign #20: Issue #2509 labeled by hello-11
December 10, 2024 06:48 2s
December 10, 2024 06:48 2s
int8 slower than bf16 on A100 auto-assign #19: Issue #2553 labeled by nv-guomingz
December 10, 2024 06:32 45s
December 10, 2024 06:32 45s