Skip to content

Pull requests: vllm-project/vllm-gguf-plugin

New pull request New
19 Open 94 Closed
19 Open 94 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

[Models] Support DeepSeek-V4 GGUF weights mapping and architecture fa…
#126 opened Sep 7, 2026 by DjoserKhemSimeu Loading…
2 tasks done
fix(moe_vec): chunk launches when tokens*top_k exceeds gridDim.z limit
#125 opened Sep 1, 2026 by BruceLoveDecimal Loading…
[Models] Support Kimi-K3 multimodal GGUF
#121 opened Aug 25, 2026 by Isotr0py Member • Draft
[Models] Serve Qwen3.5/3.6/3.8 text-only GGUF without an mm_proj
#120 opened Aug 24, 2026 by laureano-arcanio Loading…
1
[Model] Add MiniMax-H3 diffusion GGUF support
#119 opened Aug 23, 2026 by lishunyang12 • Draft
Experimental vibecoded Gguf map tool
#118 opened Aug 21, 2026 by amd-satre • Draft
[Refactor] Drop the GGUF draft workarounds now that vLLM covers them
#117 opened Aug 21, 2026 by WhatGhost • Draft
[Models] Support the Muse Glimmer dflash draft model in GGUF
#115 opened Aug 20, 2026 by WhatGhost Loading…
Add Muse Glimmer GGUF support
#113 opened Aug 19, 2026 by WhatGhost Loading…
@Isotr0py
2
feat(weights-adapter): add DeepSeek V2/V3 GGUF adapter
#111 opened Aug 18, 2026 by Feijia1231 Contributor Loading…
fix(quantization): handle mixed-precision fused layers in is_layer_skipped_gguf
#107 opened Aug 13, 2026 by BenWongCityuCS Loading…
[Model] Add text-only Kimi-K3 GGUF support
#92 opened Jul 30, 2026 by varoudis Loading…
@Isotr0py
3
Add diffusion model serving command to readme
#90 opened Jul 21, 2026 by Isotr0py Member Loading…
Bound GGUF dequantization workspace for tall weights
#89 opened Jul 18, 2026 by estridell Loading…
2
Configure buildkite merge CI
#81 opened Jul 10, 2026 by Isotr0py Member Loading…
[Bugfix] Preserve GGUF weight path for config source lookup
#70 opened Jun 23, 2026 by lesj0610 Loading…
4 tasks done
2
Add MMQ v2 and generic model adapters
#21 opened Jun 10, 2026 by lesj0610 Loading…
2
Investigate CUDA kernel JIT compilation
#15 opened May 13, 2026 by Isotr0py Member • Draft
Configure release CI
#12 opened May 12, 2026 by Isotr0py Member Loading…
ProTip! Updated in the last three days: updated:>2026-09-04.