Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
78 Open 1,432 Closed
78 Open 1,432 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

add: GQA support to AWQ awq For any issue / PR related to AWQ support transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2818 opened Jun 10, 2026 by soyr-redhat Contributor Loading…
4 tasks done
8
feat: add handle_cache_error decorator to IntermediatesCache enhancement New feature or request
#2817 opened Jun 9, 2026 by kylesayrs Collaborator Loading…
4 tasks done
6
model/checkpoint mapping for ignore list + gemma4 example fp8 For any issue / PR related to FP8 support moe ready When a PR is ready for review
#2816 opened Jun 9, 2026 by HDCharles Collaborator Loading…
8
[QuIP] Change default to only use input (v) rotations enhancement New feature or request transforms Related to transforms-based modifiers like SpinQuant and Quip
#2815 opened Jun 9, 2026 by kylesayrs Collaborator Loading…
9
fix: cpu offload hits OOM awq For any issue / PR related to AWQ support bug Something isn't working model_free_ptq For any PR/issue related to the `model_free_ptq` pathway two-reviews When a PR requires two reviews
#2813 opened Jun 9, 2026 by JINO-ROHIT Contributor Loading…
1
8
Add Mistral 4 MoE calibration support enhancement New feature or request moe needs-rebase tracing Issues related to model tracing transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2812 opened Jun 9, 2026 by robertforbes68 • Draft
10
Add load_context unified context manager enhancement New feature or request moe ready When a PR is ready for review
#2811 opened Jun 9, 2026 by kylesayrs Collaborator Loading…
5
Update dep versions for release enhancement New feature or request two-reviews When a PR requires two reviews
#2810 opened Jun 9, 2026 by dhuangnm Collaborator Loading…
10
[Agents] Configure coderabbit enhancement New feature or request
#2809 opened Jun 9, 2026 by kylesayrs Collaborator Loading…
8
[Skill] Automated PR Validator
#2804 opened Jun 5, 2026 by brian-dellabetta Collaborator • Draft
3 of 5 tasks
11
Add OlmoForCausalLM (v1/v2) AWQ mapping using exaone4-style awq For any issue / PR related to AWQ support requires-validate Indicates that a PR looks appropriate, but needs to be run before merging transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2802 opened Jun 4, 2026 by HumphreySun98 Loading…
4
Add ArceeForCausalLM mappings for AWQ and SmoothQuant awq For any issue / PR related to AWQ support enhancement New feature or request requires-validate Indicates that a PR looks appropriate, but needs to be run before merging smoothquant For any issue / PR related to SmoothQuant support transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2801 opened Jun 4, 2026 by HumphreySun98 Loading…
4
Add MoE architectures to SmoothQuant registry (attention-only) enhancement New feature or request moe requires-validate Indicates that a PR looks appropriate, but needs to be run before merging smoothquant For any issue / PR related to SmoothQuant support transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2800 opened Jun 4, 2026 by HumphreySun98 Loading…
13
Add StablelmForCausalLM mappings for AWQ and SmoothQuant awq For any issue / PR related to AWQ support enhancement New feature or request requires-validate Indicates that a PR looks appropriate, but needs to be run before merging smoothquant For any issue / PR related to SmoothQuant support transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2799 opened Jun 4, 2026 by HumphreySun98 Loading…
7
fix: re-tie word embeddings before save to avoid duplicate lm_head bug Something isn't working quality-failed ready When a PR is ready for review transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2798 opened Jun 4, 2026 by EdalatiAli Loading…
12
Add GraniteForCausalLM mappings for AWQ and SmoothQuant awq For any issue / PR related to AWQ support enhancement New feature or request requires-validate Indicates that a PR looks appropriate, but needs to be run before merging smoothquant For any issue / PR related to SmoothQuant support transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2797 opened Jun 4, 2026 by HumphreySun98 Loading…
4
[model_free_ptq] Perform validation on meta device model_free_ptq For any PR/issue related to the `model_free_ptq` pathway
#2796 opened Jun 4, 2026 by kylesayrs Collaborator Loading…
7
[ZENDNN] Added support for qwen 3.6 W8A8
#2789 opened Jun 2, 2026 by Priyjain-amd • Draft
1
7
[Distributed] Module parallel calibration for QuantizationModifier
#2785 opened Jun 2, 2026 by kylesayrs Collaborator Loading…
7
[Lifecycle] Add modules argument to on_sequential_epoch_end
#2784 opened Jun 2, 2026 by kylesayrs Collaborator Loading…
3
[Lifecycle] Make calibration events first-class citizens awq For any issue / PR related to AWQ support gptq For any PR / issue related to GPTQ support ready When a PR is ready for review smoothquant For any issue / PR related to SmoothQuant support transforms Related to transforms-based modifiers like SpinQuant and Quip two-reviews When a PR requires two reviews
#2783 opened Jun 2, 2026 by kylesayrs Collaborator Loading…
13
[Misc] Remove oneshot output_dir warning enhancement New feature or request
#2782 opened Jun 2, 2026 by kylesayrs Collaborator Loading…
7
[Tests] Sampling params for E2E tests enhancement New feature or request
#2780 opened Jun 1, 2026 by kylesayrs Collaborator • Draft
9
[XPU] Add torch.cuda linter Refactor Code cleanup and/or improvements to existing features
#2776 opened Jun 1, 2026 by kylesayrs Collaborator • Draft
25
refactor: modernize utils, pipeline, and observers modules with Python 3.10+ type hints needs-rebase Refactor Code cleanup and/or improvements to existing features two-reviews When a PR requires two reviews
#2775 opened Jun 1, 2026 by AsadShahid04 Contributor Loading…
1
12
ProTip! Exclude everything labeled bug with -label:bug.