Skip to content

Actions: NVIDIA/TensorRT-LLM

Blossom-CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
275 workflow runs
275 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Medusa performance degrades with batch size larger than 1
Blossom-CI #100: Issue comment #2482 (comment) created by hello-11
December 10, 2024 07:02 4s
December 10, 2024 07:02 4s
[Question] Running custom Encoder Decoder model
Blossom-CI #99: Issue comment #2491 (comment) created by yuekaizhang
December 10, 2024 06:50 4s
December 10, 2024 06:50 4s
Failed to install by poetry add
Blossom-CI #98: Issue comment #2515 (comment) created by hello-11
December 10, 2024 06:41 4s
December 10, 2024 06:41 4s
How to extract the hidden_states before output_ids during the inference process.
Blossom-CI #97: Issue comment #2499 (comment) created by hello-11
December 10, 2024 06:12 4s
December 10, 2024 06:12 4s
[QST] How to get the prefill latency and TPOT resepectly when using C++ runtime
Blossom-CI #96: Issue comment #2500 (comment) created by hello-11
December 10, 2024 05:51 4s
December 10, 2024 05:51 4s
[Question] Running custom Encoder Decoder model
Blossom-CI #95: Issue comment #2491 (comment) created by hello-11
December 10, 2024 04:56 4s
December 10, 2024 04:56 4s
int4 not faster than fp16 and fp8
Blossom-CI #94: Issue comment #2487 (comment) created by Tracin
December 10, 2024 03:25 5s
December 10, 2024 03:25 5s
Issues with installing on Windows
Blossom-CI #93: Issue comment #2489 (comment) created by hello-11
December 10, 2024 03:25 6s
December 10, 2024 03:25 6s
How to install tensorrt-llm in python3.11?
Blossom-CI #92: Issue comment #2481 (comment) created by hello-11
December 10, 2024 02:57 4s
December 10, 2024 02:57 4s
Blossom-CI
Blossom-CI #89: created by hoangphuc1998
December 9, 2024 11:58 5s
December 9, 2024 11:58 5s
Windows C++ Executor on v0.10.0
Blossom-CI #88: Issue comment #2457 (comment) created by hello-11
December 9, 2024 09:32 5s
December 9, 2024 09:32 5s
LayerInfo doesn't support fp8 and int4_awq dtype?
Blossom-CI #87: Issue comment #2547 (comment) created by youki-sada
December 9, 2024 08:57 5s
December 9, 2024 08:57 5s
Didn't find wheel for tensorrt-llm
Blossom-CI #86: Issue comment #2181 (comment) created by arivero
December 8, 2024 22:36 4s
December 8, 2024 22:36 4s
Blossom-CI
Blossom-CI #85: created by arivero
December 8, 2024 22:02 5s
December 8, 2024 22:02 5s
trtllm-serve does not support dynamic batching like tritonserver
Blossom-CI #84: Issue comment #2549 (comment) created by njaramish
December 7, 2024 18:54 4s
December 7, 2024 18:54 4s
Wrong output on Llama 3.2 1B, but 3B ok
Blossom-CI #83: Issue comment #2492 (comment) created by jayakommuru
December 7, 2024 17:13 4s
December 7, 2024 17:13 4s
Wrong output on Llama 3.2 1B, but 3B ok
Blossom-CI #82: Issue comment #2492 (comment) created by jayakommuru
December 7, 2024 17:12 4s
December 7, 2024 17:12 4s
Qwen2-VL Batch Bug
Blossom-CI #81: Issue comment #2495 (comment) created by alimgl-pixel
December 7, 2024 02:52 4s
December 7, 2024 02:52 4s
Blossom-CI
Blossom-CI #80: created by aabbhishekksr
December 6, 2024 14:52 6s
December 6, 2024 14:52 6s
Qwen2-VL Batch Bug
Blossom-CI #79: Issue comment #2495 (comment) created by YSF-A
December 6, 2024 09:56 5s
December 6, 2024 09:56 5s
How to visualize network?
Blossom-CI #77: Issue comment #2501 (comment) created by youki-sada
December 6, 2024 08:17 4s
December 6, 2024 08:17 4s
pip install errors out with HTTP error 404
Blossom-CI #76: Issue comment #2542 (comment) created by TriDefender
December 6, 2024 02:23 5s
December 6, 2024 02:23 5s