Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

auto-assign

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support for int2/int3 quantization auto-assign #128: Issue #2704 labeled by nv-guomingz
January 20, 2025 05:26 43s
January 20, 2025 05:26 43s
SmoothQuant doesn't work with lora auto-assign #127: Issue #2604 labeled by byshiue
January 20, 2025 03:42 2s
January 20, 2025 03:42 2s
Wrong outputs with FP8 kv_cache reuse auto-assign #126: Issue #2699 labeled by lishicheng1996
January 16, 2025 11:58 3s
January 16, 2025 11:58 3s
Custom allreduce performance improvement auto-assign #125: Issue #2696 labeled by nv-guomingz
January 16, 2025 04:05 42s
January 16, 2025 04:05 42s
Failed TensorRT-LLM Benchmark auto-assign #124: Issue #2694 labeled by maulikmadhavi
January 15, 2025 10:41 3s
January 15, 2025 10:41 3s
0.16.0 Qwen2-72B-Struct SQ error auto-assign #123: Issue #2693 labeled by gy0514020329
January 15, 2025 07:00 2s
January 15, 2025 07:00 2s
NotImplementedError: Cannot copy out of meta tensor; no data! auto-assign #122: Issue #2692 labeled by chilljudaoren
January 15, 2025 03:05 3s
January 15, 2025 03:05 3s
Deepseek-v3 int4 weight only inference outputs garbage words with TP 8 on nvidia H20 GPU auto-assign #121: Issue #2683 labeled by nv-guomingz
January 14, 2025 14:35 1m 7s
January 14, 2025 14:35 1m 7s
internvl-2.5 auto-assign #120: Issue #2686 labeled by nv-guomingz
January 14, 2025 14:31 3s
January 14, 2025 14:31 3s
Multi-LoRA cpp inference error: Assertion failed: lora_weights has to few values for attn_k auto-assign #119: Issue #2687 labeled by nv-guomingz
January 14, 2025 14:29 52s
January 14, 2025 14:29 52s
trtllm-build llama3.1-8b failed auto-assign #118: Issue #2688 labeled by nv-guomingz
January 14, 2025 14:29 46s
January 14, 2025 14:29 46s
(Memory leak) trtllm-build gets OOM without GPTAttentionPlugin auto-assign #117: Issue #2690 labeled by idantene
January 14, 2025 09:51 2s
January 14, 2025 09:51 2s
Wrong output shapes in Whisper encoder auto-assign #116: Issue #2689 labeled by MahmoudAshraf97
January 14, 2025 09:06 3s
January 14, 2025 09:06 3s
Inference error encountered while using the draft target model. auto-assign #115: Issue #2684 labeled by pimang62
January 13, 2025 09:46 3s
January 13, 2025 09:46 3s
Llama-3.2 SmoothQuant convert checkpoint error auto-assign #114: Issue #2677 labeled by nv-guomingz
January 13, 2025 06:34 43s
January 13, 2025 06:34 43s
Inference Qwen2-0.5b + Medusa failed auto-assign #113: Issue #2678 labeled by nv-guomingz
January 13, 2025 06:33 47s
January 13, 2025 06:33 47s
How to use multiple GPUs to infer qwen? auto-assign #112: Issue #2680 labeled by nv-guomingz
January 13, 2025 06:31 2s
January 13, 2025 06:31 2s
Error when building the TRT engine on InternVL2 examples auto-assign #111: Issue #2679 labeled by nv-guomingz
January 13, 2025 06:29 2s
January 13, 2025 06:29 2s
Error when building the TRT engine on InternVL2 examples auto-assign #110: Issue #2679 labeled by nv-guomingz
January 13, 2025 06:29 45s
January 13, 2025 06:29 45s
the difference of quantization implementation between quantize.py and convert_checkpoint.py auto-assign #109: Issue #2681 labeled by nv-guomingz
January 13, 2025 06:28 1s
January 13, 2025 06:28 1s
Error when building the TRT engine on InternVL2 examples auto-assign #108: Issue #2679 labeled by StMarou
January 10, 2025 10:26 3s
January 10, 2025 10:26 3s
Inference Qwen2-0.5b + Medusa failed auto-assign #107: Issue #2678 labeled by shangshng
January 10, 2025 08:02 3s
January 10, 2025 08:02 3s
Llama-3.2 SmoothQuant convert checkpoint error auto-assign #106: Issue #2677 labeled by lyffly
January 10, 2025 02:39 2s
January 10, 2025 02:39 2s
Difference in attention output when compared to HF engine attention output result. auto-assign #105: Issue #2675 labeled by krishnanpooja
January 9, 2025 10:12 3s
January 9, 2025 10:12 3s
EAGLE model seems to be deployed but raises an error on inference auto-assign #104: Issue #2673 labeled by nuxlear
January 9, 2025 02:01 2s
January 9, 2025 02:01 2s