Skip to content

Pull requests: GeeeekExplorer/nano-vllm

New pull request New
46 Open 86 Closed
46 Open 86 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: add fp8 (e4m3) weight-only quantization
#241 opened Jun 10, 2026 by HaozheZhang6 Loading…
Change return type from list[str] to list[dict]
#238 opened Jun 4, 2026 by ZhengWentong Loading…
add qwen3-moe
#236 opened May 29, 2026 by shhyQAQ Loading…
set up uv env
#235 opened May 26, 2026 by hchen549 Loading…
1
Fix prefix cache OOB in prepare_prefill when num_cached_tokens grows during allocate
#233 opened May 17, 2026 by yuanmouya-prog Loading…
Add Qwen3.5 (text + multimodal) support
#232 opened May 13, 2026 by 86MaxCao Loading…
Add SDPA attention fallback and design docs
#231 opened May 12, 2026 by Lebhoryi Loading…
feat: Add int8 KV cache compression with head-major layout and async pipelining
#229 opened May 8, 2026 by naalo2 Loading…
1
refactor the attention with cutile
#227 opened May 8, 2026 by chakpongchung • Draft
fix(model_runner): all_reduce num_kvcache_blocks to MIN across TP ranks
#215 opened Apr 24, 2026 by Anai-Guo Contributor Loading…
1
1
fix: normalize legacy rope_scaling to rope_parameters
#214 opened Apr 24, 2026 by cuber726579 Loading…
fix(scheduler): resolve out-of-bounds error during prefix cache hit after sequence preemption
#211 opened Apr 22, 2026 by wangyuzhuo116 Loading…
2 tasks done
1
fix: recompute scheduled tokens after prefix-cache allocation
#210 opened Apr 22, 2026 by tj1235 Loading…
1
Fix RMSNorm fp32 input mutation
#205 opened Apr 14, 2026 by JxKim Loading…
1
feat: add PD disaggregated prefill stub implementation based on vllm-…
#202 opened Apr 12, 2026 by SunChenxiang123 Loading…
feat: add CPU offload connector stubs for KV cache GPU↔CPU transfer
#201 opened Apr 12, 2026 by SunChenxiang123 Loading…
fix: pass rope_scaling=None for Qwen3 to avoid unhashable dict error
#198 opened Apr 9, 2026 by CruxZhou Loading…
1
[Feat] Add PyTorch Profiler support for performance analysis
#193 opened Mar 31, 2026 by RagingSilence 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…
1
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
ProTip! Filter pull requests by the default branch with base:main.