Skip to content

Pull requests: GeeeekExplorer/nano-vllm

New pull request New
43 Open 58 Closed
43 Open 58 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

Fix scheduler.postprocess return type
#200 opened Apr 11, 2026 by KinglittleQ Loading…
fix(engine): resolve crash on fully cached (100% match) prompt via L-1 fallback strategy
#199 opened Apr 10, 2026 by fishAndShrimp Loading…
fix: pass rope_scaling=None for Qwen3 to avoid unhashable dict error
#198 opened Apr 9, 2026 by CruxZhou Loading…
1
docs: use hf download in README
#194 opened Apr 2, 2026 by sablecode Loading…
1
[Feat] Add PyTorch Profiler support for performance analysis
#193 opened Mar 31, 2026 by RagingSilence Loading…
fix: correct postprocess return type annotation
#192 opened Mar 30, 2026 by Desirer Loading…
Fix CUDA graph block_tables shape mismatch
#191 opened Mar 24, 2026 by ilrewrite Loading…
1
Feature/support llama3
#188 opened Mar 21, 2026 by wudong5 Loading…
fix: update download command for model weights in README
#185 opened Mar 12, 2026 by SYaoJun Loading…
feat: INT8 KV cache quantization (~48% memory reduction)
#184 opened Mar 9, 2026 by dzhengAP Loading…
docs: add Chinese README and language links
#183 opened Mar 8, 2026 by LJS1124 Loading…
fix: rope_scaling unhashable dict error with transformers>=5.1.0
#182 opened Mar 8, 2026 by chenwenxiaolive Loading…
1 task done
1
3
refactor(block_manager): replace numpy with array for token ID hashing
#180 opened Mar 7, 2026 by fly1989 Loading…
1
add a Dockerfile for nano-vllm
#178 opened Mar 3, 2026 by pacoxu Loading…
[Doc]Add Repository Architecture Overview Document
#177 opened Feb 26, 2026 by CalvinXKY Loading…
Avoid per-step allocations in CUDA-graph decode(fix #175)
#176 opened Feb 23, 2026 by MrAnayDongre Loading…
1
2
Update embed_head.py
#174 opened Feb 21, 2026 by TianduoWang Loading…
enable 'slots=True' for dataclasses
#172 opened Feb 9, 2026 by IceCreamMilkyTea Loading…
fix: modify input when input is fp32
#171 opened Feb 8, 2026 by philhuan Loading…
1
fix(rms_norm): add copy for residual
#169 opened Jan 28, 2026 by tpoisonooo Loading…
test
#160 opened Jan 15, 2026 by volcano98 Loading…
fix: clean up hash_to_block_id mapping when deallocating blocks
#153 opened Jan 6, 2026 by ggboooy Loading…
3
remove hard code for block_size
#148 opened Dec 29, 2025 by guodongxiaren Loading…
bug for tensor parallelism # issue 144
#145 opened Dec 17, 2025 by LiaoMengqi Loading…
2
Fix: unsqueeze on the last dim for VocabParallelEmbedding
#142 opened Dec 10, 2025 by ljwljwljwljw Loading…
ProTip! What’s not been updated in a month: updated:<2026-03-12.