Skip to content

Pull requests: Samsung/TICO

New pull request New
23 Open 438 Closed
23 Open 438 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

[quantization] Fix quant_vision_patch_merger
#616 opened Apr 9, 2026 by Torrero Loading…
Trace data flow through Qwen3VL submodules
#615 opened Apr 9, 2026 by dvsav Contributor • Draft
[quantization] Move prefill logic
#613 opened Apr 6, 2026 by stamalakhov Contributor Loading…
@stamalakhov
[quantization] [draft] Introduce smse_for_gptq
#597 opened Mar 31, 2026 by stamalakhov Contributor • Draft
@stamalakhov
[quatization][DRAFT] Quantize Qwen3VLVisionAttention DRAFT No merge
#584 opened Mar 26, 2026 by CMDR-DiTRay Contributor • Draft
1
[quantization][draft] Prefill-decode logic
#570 opened Mar 23, 2026 by stamalakhov Contributor • Draft
@stamalakhov
[quantization] Introduce wrappers for Qwen3VLTextDecoderLayer and Qwen3VLTextModel
#535 opened Mar 5, 2026 by dayo09 Contributor • Draft
10
[passes] Introduce ConvertPermuteToReshape pass No merge
#521 opened Feb 25, 2026 by llFreetimell Contributor Loading…
8
[passes] Optimize ConvertConv3dToConv2d for special case No merge
#518 opened Feb 25, 2026 by llFreetimell Contributor Loading…
5
[DRAFT][passes] Passes and tests for VLM PatchEmbed optimization DRAFT No merge
#517 opened Feb 25, 2026 by llFreetimell Contributor • Draft
1
[quantization] Introduce wrapper for Qwen3VLTextRotaryEmbedding
#498 opened Feb 17, 2026 by dvsav Contributor • Draft
2
[quantization] Introduce wrapper for Qwen3VLVisionRotaryEmbedding
#496 opened Feb 16, 2026 by dvsav Contributor • Draft
7
[passes] Support torch.linspace
#453 opened Jan 30, 2026 by dayo09 Contributor • Draft
[DRAFT][quantization] Full quantization of LLama compatible models DRAFT
#436 opened Jan 13, 2026 by stamalakhov Contributor • Draft
@stamalakhov
29
Support SymSize Lowering
#425 opened Nov 27, 2025 by dayo09 Contributor • Draft
PoC: Convert cond
#330 opened Sep 10, 2025 by dayo09 Contributor • Draft
3
[passes] Revise LlamaRMSNorm fusion DRAFT
#304 opened Aug 29, 2025 by seockho-kim Contributor • Draft
DRAFT: [serialize] Support item operation
#302 opened Aug 28, 2025 by dayo09 Contributor • Draft
DRAFT: [serialize] Enable dynamic shape in copy operator
#281 opened Aug 13, 2025 by dayo09 Contributor • Draft
1
Support TopK operator DRAFT
#275 opened Aug 11, 2025 by dayo09 Contributor • Draft
Remove redundant ignore
#262 opened Aug 1, 2025 by dayo09 Contributor • Draft
DRAFT: Refactor test.utils.tag
#242 opened Jul 23, 2025 by dayo09 Contributor • Draft
Add capabilities to test models with dynamic inputs
#35 opened Apr 9, 2025 by mbencer • Draft
1
ProTip! Filter pull requests by the default branch with base:main.