Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
63 Open 234 Closed
63 Open 234 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fixed == -> = typo
#1958 opened Jul 16, 2024 by mrdrprofuroboros Loading…
chore(docs): fix typos
#1939 opened Jul 12, 2024 by lfz941 Loading…
chore: remove duplicate flag
#1937 opened Jul 12, 2024 by hattizai Loading…
Correct the version
#1936 opened Jul 12, 2024 by Shixiaowei02 Loading…
Fix default min length
#1935 opened Jul 11, 2024 by akhoroshev Loading…
Add support for custom tokenizer and batch size
#1927 opened Jul 9, 2024 by uppalutkarsh Loading…
Add support for falcon2
#1926 opened Jul 9, 2024 by puneeshkhanna Loading…
1
add chunk_length parameter to Whisper
#1909 opened Jul 7, 2024 by MahmoudAshraf97 Loading…
4
Update setup_build_env.ps1
#1902 opened Jul 5, 2024 by nero-dv Loading…
Support gelu_pytorch_tanh activation function Merged
#1897 opened Jul 4, 2024 by ttim Loading…
Dev sm87 trt101
#1880 opened Jul 3, 2024 by sunnyqgg Loading…
DeepSeek MoE support triaged Issue has been triaged by maintainers
#1758 opened Jun 9, 2024 by akhoroshev Loading…
@dominicshanshan
12
Bump transformers from 4.36.2 to 4.38.0 in /examples/multimodal bug Something isn't working dependencies Pull requests that update a dependency file triaged Issue has been triaged by maintainers waiting for feedback
#1689 opened May 28, 2024 by dependabot bot Loading…
@byshiue
2
add cached generation buffer triaged Issue has been triaged by maintainers waiting for feedback
#1685 opened May 28, 2024 by michael200892458 Loading…
@byshiue
1
Optimize python benchmark logging triaged Issue has been triaged by maintainers
#1646 opened May 22, 2024 by michaelnny Loading…
@byshiue
2
Fix CUDA OOM when creating Mixtral checkpoint triaged Issue has been triaged by maintainers waiting for feedback
#1629 opened May 19, 2024 by VivekBits2210 Loading…
@byshiue
2
Add support for non-power-of-two heads with Alibi triaged Issue has been triaged by maintainers
#1611 opened May 15, 2024 by vmarkovtsev Loading…
@byshiue @jaedeok-nvidia
2
[feat]: Support weight only gemm with 2bit triaged Issue has been triaged by maintainers waiting for feedback
#1568 opened May 9, 2024 by gavinchen430 Loading…
@byshiue
4
Use first bad_words as extra parameters, and implement min-p
#1536 opened May 2, 2024 by pathorn • Draft
2
Support SDXL and its distributed inference waiting for feedback
#1514 opened Apr 28, 2024 by Zars19 Loading…
6
Remove the <s> token from post_prompt of multimodal
#1508 opened Apr 26, 2024 by yupbank Loading…
1
fix: correct cudaSetDevice error when GPUs per node are fewer than their ranks in inter-node inference
#1495 opened Apr 24, 2024 by littlefatfat Loading…
1
llama convert add rotary_scaling param in cli_args waiting for feedback
#1385 opened Apr 1, 2024 by activezhao Loading…
2
Add SmoothQuant for T5 (decoder only right now)
#1366 opened Mar 27, 2024 by eycheung Loading…
2
Relax python dependencies triaged Issue has been triaged by maintainers
#1346 opened Mar 24, 2024 by tdeboissiere Loading…
@byshiue
1
ProTip! Updated in the last three days: updated:>2024-07-13.