Skip to content

Pull requests: neuralmagic/nm-vllm

New pull request New
30 Open 219 Closed
30 Open 219 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

updates for automation (and release)
#265 opened May 23, 2024 by andy-neuma Loading…
4
update install commands
#264 opened May 23, 2024 by dhuangnm Loading…
2
Fix quantization rounding
#263 opened May 22, 2024 by varun-sundar-rabindranath Loading…
Update Dockerfile for the release
#262 opened May 22, 2024 by dhuangnm Loading…
1
Address py38/39 incompatibilities
#261 opened May 22, 2024 by dbarbuzzi Loading…
@dbarbuzzi
4
Lwilkinson/metrics expansion
#258 opened May 22, 2024 by LucasWilkinson • Draft
Upstream sync 2024 05 19
#249 opened May 19, 2024 by robertgshaw2-neuralmagic Loading…
Reasonable int8 configs
#238 opened May 13, 2024 by varun-sundar-rabindranath Loading…
[CI/Build] Basic server correctness test
#237 opened May 13, 2024 by derekk-nm • Draft
@dbarbuzzi @dhuangnm @robertgshaw2-neuralmagic
5
Skipping refactor
#234 opened May 13, 2024 by robertgshaw2-neuralmagic Loading…
Create test_optional_libraries.py
#230 opened May 9, 2024 by mgoin Loading…
[Activation Quantization] Dynamic Per Token Support
#225 opened May 6, 2024 by dsikka Loading…
2
Initial CompressedTensors config + Activation Quantization support …
#219 opened Apr 30, 2024 by dsikka Loading…
Torch compile fusion backend prototype
#209 opened Apr 25, 2024 by bnellnm • Draft
[WIP] Please do not delete - comparing changes between branches
#203 opened Apr 23, 2024 by afeldman-nm Loading…
[WIP] FLAN-T5 integration
#194 opened Apr 17, 2024 by afeldman-nm Loading…
WIP: basic correctness test
#192 opened Apr 17, 2024 by derekk-nm • Draft
41
whl centric
#191 opened Apr 17, 2024 by andy-neuma Loading…
Prototype FP8Linear W8A8 runtime quantization
#190 opened Apr 15, 2024 by mgoin • Draft
Entrypoint for hosting local Kobold Lite chat interface
#184 opened Apr 12, 2024 by mgoin Loading…
3
Added Docker Compose Example
#182 opened Apr 12, 2024 by robertgshaw2-neuralmagic Loading…
16
vllm - quantization : DO NOT MERGE
#180 opened Apr 11, 2024 by varun-sundar-rabindranath Loading…
Pypi and updates
#177 opened Apr 9, 2024 by andy-neuma Loading…
[WIP] Upstream encoder/decoder support based on multiple blocktables
#161 opened Apr 2, 2024 by afeldman-nm • Draft
Support for compressed-tensors
#159 opened Apr 2, 2024 by dbogunowicz Loading…
27
ProTip! Add no:assignee to see everything that’s not assigned.