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

how to avoid oom when inference qwen2-vl 7B with batch=2?
Blossom-CI #125: Issue comment #2496 (comment) created by sunnyqgg
December 11, 2024 08:58 5s
December 11, 2024 08:58 5s
Qwen2-VL Batch Bug
Blossom-CI #124: Issue comment #2495 (comment) created by sunnyqgg
December 11, 2024 08:54 4s
December 11, 2024 08:54 4s
Qwen2-VL FP8/INT8 Quantization
Blossom-CI #123: Issue comment #2546 (comment) created by sunnyqgg
December 11, 2024 08:49 5s
December 11, 2024 08:49 5s
Qwen2_VL profiling: TRT model low performance
Blossom-CI #122: Issue comment #2551 (comment) created by sunnyqgg
December 11, 2024 08:47 5s
December 11, 2024 08:47 5s
Issue with converting custom encoder model
Blossom-CI #121: Issue comment #2535 (comment) created by yuekaizhang
December 11, 2024 08:37 5s
December 11, 2024 08:37 5s
Issue with converting custom encoder model
Blossom-CI #120: Issue comment #2535 (comment) created by AvivSham
December 11, 2024 08:04 5s
December 11, 2024 08:04 5s
Issue with converting custom encoder model
Blossom-CI #119: Issue comment #2535 (comment) created by yuekaizhang
December 11, 2024 07:40 4s
December 11, 2024 07:40 4s
Issue with converting custom encoder model
Blossom-CI #118: Issue comment #2535 (comment) created by AvivSham
December 11, 2024 07:33 5s
December 11, 2024 07:33 5s
Issue with converting custom encoder model
Blossom-CI #117: Issue comment #2535 (comment) created by yuekaizhang
December 11, 2024 07:20 5s
December 11, 2024 07:20 5s
Blossom-CI
Blossom-CI #116: created by CN-COTER
December 11, 2024 07:14 4s
December 11, 2024 07:14 4s
[Question] Running custom Encoder Decoder model
Blossom-CI #115: Issue comment #2491 (comment) created by AvivSham
December 11, 2024 07:05 4s
December 11, 2024 07:05 4s
Issue with converting custom encoder model
Blossom-CI #114: Issue comment #2535 (comment) created by AvivSham
December 11, 2024 07:04 4s
December 11, 2024 07:04 4s
Issues with installing on Windows
Blossom-CI #113: Issue comment #2489 (comment) created by PyroGenesis
December 10, 2024 20:11 5s
December 10, 2024 20:11 5s
int4 not faster than fp16 and fp8
Blossom-CI #112: Issue comment #2487 (comment) created by ShuaiShao93
December 10, 2024 19:49 5s
December 10, 2024 19:49 5s
Blossom-CI
Blossom-CI #111: created by ShuaiShao93
December 10, 2024 18:47 5s
December 10, 2024 18:47 5s
Inconsistency with penaltyKernels.cu
Blossom-CI #110: Issue comment #2486 (comment) created by buddhapuneeth
December 10, 2024 18:22 5s
December 10, 2024 18:22 5s
Build fails on w8a8 with kv_cache_dtype FP8
Blossom-CI #109: Issue comment #2559 (comment) created by darraghdog
December 10, 2024 17:34 5s
December 10, 2024 17:34 5s
Performance issue with batching
Blossom-CI #108: Issue comment #2466 (comment) created by ShuaiShao93
December 10, 2024 17:26 5s
December 10, 2024 17:26 5s
How to use greedy search correctly
Blossom-CI #107: Issue comment #2557 (comment) created by fan-niu
December 10, 2024 14:55 5s
December 10, 2024 14:55 5s
How to use greedy search correctly
Blossom-CI #106: Issue comment #2557 (comment) created by akhoroshev
December 10, 2024 14:28 5s
December 10, 2024 14:28 5s
Inconsistency with penaltyKernels.cu
Blossom-CI #105: Issue comment #2486 (comment) created by buddhapuneeth
December 10, 2024 13:05 5s
December 10, 2024 13:05 5s
December 10, 2024 08:26 5s
Medusa performance degrades with batch size larger than 1
Blossom-CI #102: Issue comment #2482 (comment) created by yweng0828
December 10, 2024 07:15 4s
December 10, 2024 07:15 4s
Performance issue with batching
Blossom-CI #101: Issue comment #2466 (comment) created by hello-11
December 10, 2024 07:07 5s
December 10, 2024 07:07 5s