Skip to content

Pull requests: vllm-project/semantic-router

New pull request New
104 Open 1,383 Closed
104 Open 1,383 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

[Router] Fix selection embeddings for non-qwen3 model_type
#2192 opened Jun 15, 2026 by WUKUNTAI-0211 Collaborator Loading…
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
4
[Bindings] Refactor onnx multimodal output extraction
#2190 opened Jun 15, 2026 by WUKUNTAI-0211 Collaborator Loading…
@rootfs @abdallahsamabd
@Xunzhuo @asaadbalum @szedan-rh
3
docs(vllm-sr): document model list command
#2187 opened Jun 14, 2026 by leno23 Loading…
1
@yehuditkerido @Xunzhuo
@liavweiss @noalimoy @haowu1234 @szedan-rh
4
[CI/Build] Run CI-safe Rust lib tests
#2186 opened Jun 14, 2026 by brelance Contributor Loading…
1
@rootfs @samzong
@Xunzhuo @yuluo-yx
3
[CI/Build] refresh precommit-local image before running
#2179 opened Jun 14, 2026 by xiaotian-yu Contributor Loading…
3 of 4 tasks
1
@samzong @Xunzhuo @yuluo-yx
3
[CLI] add 'vllm-sr rag list' to list ingested vector stores
#2178 opened Jun 13, 2026 by WUKUNTAI-0211 Collaborator Loading…
1
@yehuditkerido @Xunzhuo
@liavweiss @noalimoy @haowu1234 @szedan-rh
5
[project] Align homepage team with governance
#2177 opened Jun 13, 2026 by Xunzhuo Member Loading…
@samzong @Xunzhuo @yuluo-yx
7
[Router] fix deepseek official thinking mode
#2175 opened Jun 13, 2026 by brelance Contributor Loading…
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Router] Optimize CountTokensApprox to avoid constructing intermediate slices
#2171 opened Jun 12, 2026 by cryo-zd Collaborator Loading…
4 tasks
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
4
[CI/Build] Add agent memory review CI gates
#2169 opened Jun 12, 2026 by nagisa-kunhah • Draft
5 tasks done
1
@rootfs @samzong
@Xunzhuo @yuluo-yx
23
[Router] Dedup query-embedding inference on the cache-miss path (in-memory backend)
#2162 opened Jun 12, 2026 by theohsiung Contributor Loading…
3 tasks done
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Bindings] Implement causal masking in the chunked-SDPA kernel
#2159 opened Jun 11, 2026 by Peterren Contributor Loading…
@rootfs @Xunzhuo
@noalimoy @haowu1234 @asaadbalum @szedan-rh
3
[Docs][CI/Build] Sync zh-Hans translation status checks
#2156 opened Jun 11, 2026 by wilsonwu Contributor Loading…
4 tasks done
@rootfs @samzong
@Xunzhuo @yuluo-yx
4
[Router] fix router_replay history 413 on large requests (bound list response + safer default)
#2155 opened Jun 11, 2026 by siloteemu Contributor Loading…
@yossiovadia @rootfs
@yehuditkerido @abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
4
[Router] preserve thinking and tool_choice.disable_parallel_tool_use on Anthropic→Anthropic path
#2153 opened Jun 11, 2026 by siloteemu Contributor Loading…
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Dashboard] Improve signal config enum and domain selection controls
#2152 opened Jun 11, 2026 by wilsonwu Contributor Loading…
4 tasks done
@yehuditkerido @Xunzhuo
@haowu1234 @JaredforReal @szedan-rh
5
[Router] Preserve structured system content in RAG system_prompt injection
#2149 opened Jun 11, 2026 by theohsiung Contributor Loading…
3 tasks done
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Router] Add RAG result-count, truncation, and typed-error metrics
#2146 opened Jun 10, 2026 by Peterren Contributor Loading…
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Router] Re-normalize truncated FFI embeddings
#2145 opened Jun 10, 2026 by WUKUNTAI-0211 Collaborator Loading…
@rootfs @Xunzhuo
@noalimoy @haowu1234 @asaadbalum @szedan-rh
8
[Router] Validate semantic_cache similarity_threshold range
#2143 opened Jun 10, 2026 by theohsiung Contributor Loading…
3 tasks done
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Router] Preserve reasoning_content when caching streaming responses
#2141 opened Jun 10, 2026 by theohsiung Contributor Loading…
3 tasks done
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
4
[Router] Escape user id in Milvus memory filter expressions (injection fix)
#2139 opened Jun 10, 2026 by theohsiung Contributor Loading…
2 of 3 tasks
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
7
[Router] Validate /api/v1/similarity input: reject blank text and out-of-range priority
#2137 opened Jun 10, 2026 by WUKUNTAI-0211 Collaborator Loading…
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
3
[Router] Enforce hard user-scope isolation in semantic cache (cross-tenant leak fix)
#2135 opened Jun 10, 2026 by theohsiung Contributor Loading…
4 of 5 tasks
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
5
[Router] Do not cache non-2xx upstream responses (cache poisoning fix)
#2131 opened Jun 10, 2026 by theohsiung Contributor Loading…
5 tasks done
1
@rootfs @yehuditkerido
@abdallahsamabd @Xunzhuo @liavweiss @noalimoy @asaadbalum @szedan-rh
6
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.