Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
33 Open 196 Closed
33 Open 196 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

Fix for e2e tests
#927 opened Nov 19, 2024 by horheynm Loading…
1
Use llama-1b for faster and more accessible examples
#924 opened Nov 19, 2024 by kylesayrs Loading…
@kylesayrs
3
Load Compressed Tensors Models with run_compressed=False
#923 opened Nov 18, 2024 by horheynm Loading…
6
[1/2] Expand e2e testing to prepare for lm-eval ready When a PR is ready for review
#922 opened Nov 17, 2024 by dsikka Loading…
4
Update kv_cache example ready When a PR is ready for review
#921 opened Nov 17, 2024 by dsikka Loading…
1
Actually make the run_compressed test useful ready When a PR is ready for review
#920 opened Nov 17, 2024 by dsikka Loading…
3
Move SparseGPTModifier location with backwards compatibility
#919 opened Nov 16, 2024 by kylesayrs • Draft
@kylesayrs
1
[Bugfix] Support model offloading SparseGPTQ
#918 opened Nov 16, 2024 by kylesayrs Loading…
@kylesayrs
1
Implement HooksMixin
#917 opened Nov 14, 2024 by kylesayrs Loading…
@kylesayrs
4
Kylesayrs/gptq partition
#914 opened Nov 13, 2024 by kylesayrs • Draft
Support pack_quantized format for nonuniform mixed-precision
#913 opened Nov 13, 2024 by mgoin Loading…
2
fix consecutive oneshot
#898 opened Nov 5, 2024 by horheynm Loading…
4
Allow Shortcutting Min-max Observer
#887 opened Nov 1, 2024 by kylesayrs Loading…
@kylesayrs
1
[BugFix] Fix Remaining Sparsity Test failures
#884 opened Nov 1, 2024 by dsikka • Draft
1
[SparseAutoModelForCausalLM Deprecation] Update examples
#880 opened Oct 31, 2024 by horheynm Loading…
22
[Bugfix] Correct metrics calculations
#878 opened Oct 30, 2024 by kylesayrs Loading…
@kylesayrs
1
[DO NOT MERGE] Increase Sparsity Threshold to 50% for sparse compression
#876 opened Oct 30, 2024 by rahul-tuli Loading…
5
[WIP] Adding un-/semi-structured pruning via ALPS
#874 opened Oct 29, 2024 by kayhanbehdin • Draft
FSDP utils cleanup
#854 opened Oct 19, 2024 by kylesayrs Loading…
@kylesayrs
[Bugfix] DisableKVCache Context
#834 opened Oct 9, 2024 by kylesayrs Loading…
1
@kylesayrs
9
Awq re implementation
#824 opened Oct 7, 2024 by rahul-tuli • Draft
1
Enable Sparse compression
#822 opened Oct 7, 2024 by rahul-tuli Loading…
1 of 3 tasks
19
Extend usability of calculate_offload_device_map
#768 opened Oct 2, 2024 by kylesayrs • Draft
e2e tests
#742 opened Oct 1, 2024 by horheynm Loading…
4
Add: Weight clipping to AWQModifier
#184 opened Sep 18, 2024 by rahul-tuli Loading…
1 task
ProTip! Adding no:label will show everything without a label.