Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
92 Open 152 Closed
92 Open 152 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

Fix missing link in perf-best-practices.md
#1587 opened May 13, 2024 by bloodeagle40234 Loading…
Fix the error of Ada traits for fpA_intB.
#1583 opened May 12, 2024 by JamesTheZ Loading…
[feat]: Support weight only gemm with 2bit
#1568 opened May 9, 2024 by gavinchen430 Loading…
1
Update customAllReduceKernels.cu - line 120's typo was edited
#1558 opened May 8, 2024 by sjbae1999 Loading…
Use cls variable instead of ModelRunner
#1551 opened May 7, 2024 by bloodeagle40234 Loading…
Update perf-best-practices.md
#1545 opened May 6, 2024 by sam-india-007 Loading…
[fix] export failure with CUDA driver < 526 and pynvml>=11.5.0
#1537 opened May 3, 2024 by CoderHam Loading…
Use first bad_words as extra parameters, and implement min-p
#1536 opened May 2, 2024 by pathorn • Draft
1
Loading Medusa Safetensors + AWQ Conversion correction
#1535 opened May 2, 2024 by Tushar-ml Loading…
Define hf_config explisitly for convert_hf_mpt_legacy
#1534 opened May 2, 2024 by bloodeagle40234 Loading…
Add note on build Llama v3
#1522 opened Apr 29, 2024 by sammcj Loading…
Update perf-overview.md
#1521 opened Apr 29, 2024 by snowmanwwg Loading…
Support SDXL and its distributed inference
#1514 opened Apr 28, 2024 by Zars19 Loading…
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…
[ModelRunner] Fix stop & bad word list pointer offset.
#1486 opened Apr 22, 2024 by fjosw Loading…
Update model_runner_cpp.py
#1435 opened Apr 9, 2024 by RoyHe Loading…
Update summarize.py
#1406 opened Apr 6, 2024 by biubiu3721 Loading…
serialize rotary base to config
#1403 opened Apr 4, 2024 by tonylek Loading…
Support internlm2
#1392 opened Apr 2, 2024 by RunningLeon Loading…
8
llama convert add rotary_scaling param in cli_args
#1385 opened Apr 1, 2024 by activezhao Loading…
[Doc] Fix mistral v0.1 build instructions
#1373 opened Mar 29, 2024 by minwhoo Loading…
Add SmoothQuant for T5 (decoder only right now)
#1366 opened Mar 27, 2024 by eycheung Loading…
2
Relax python dependencies
#1346 opened Mar 24, 2024 by tdeboissiere Loading…
[feat]: Add Option to convert and run distil-whisper large-v3
#1337 opened Mar 22, 2024 by IbrahimAmin1 Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.