Skip to content

Pull requests: UbiquitousLearning/mllm

New pull request New
11 Open 459 Closed
11 Open 459 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

feat(mllm_kernel): add initial implementation of mllm-kernel with CPU and JIT utilities
#634 opened Feb 3, 2026 by chenghuaWang Loading…
15
Bench/context sweep snapshot
#627 opened Feb 2, 2026 by huangzhenhua111 Loading…
Feat: implement qwen3 probing service and tests
#626 opened Feb 2, 2026 by yuerqiqi Loading…
20
tools/mllm-llm-benchmark: estimate KV cache bytes from model config
#623 opened Jan 31, 2026 by huangzhenhua111 Loading…
4
tools/mllm-llm-benchmark: add CSV output and configurable runs
#622 opened Jan 31, 2026 by huangzhenhua111 Loading…
9
feat(x86,cpu) add support for Qwen3 MoE model on x86
#619 opened Jan 30, 2026 by HayzelHan Loading…
17
tools/mllm-llm-benchmark: add llama benchmark template enhancement New feature or request
#617 opened Jan 30, 2026 by huangzhenhua111 Loading…
29
feat : Add Support of Qwen2.5Omni Model
#612 opened Jan 23, 2026 by KKkai0315 Loading…
16
feat: add support of internlm2.5-1.8B-chat model
#515 opened Nov 12, 2025 by Sp0tless Loading…
9
fix small bugs with run_qwen_npu.sh.
#295 opened Jun 12, 2025 by yinrun Loading…
feat: add Qwen2.5 0.5B Compatibility
#282 opened May 20, 2025 by kjh2159 Loading…
ProTip! Follow long discussions with comments:>50.