Skip to content

Pull requests: tobi/qmd

New pull request New
70 Open 68 Closed
70 Open 68 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: respect NODE_LLAMA_CPP_GPU and GGML_CUDA env vars for CPU-only mode
#266 opened Feb 26, 2026 by MichalSy Loading…
Bump better-sqlite3 from ^11.0.0 to ^12.4.5 (Node 25 support)
#263 opened Feb 26, 2026 by Copilot AI • Draft
1
@tobi
feat: support QMD_EMBED_MODEL and QMD_EMBED_CTX_SIZE env vars
#261 opened Feb 25, 2026 by ehc-io Loading…
feat: expose candidateLimit as MCP tool parameter and CLI flag
#255 opened Feb 24, 2026 by pandysp Loading…
2 of 4 tasks
1
fix: skip unreadable files during indexing instead of crashing
#253 opened Feb 23, 2026 by jimmynail Loading…
1
fix(mcp): support multiple concurrent client sessions
#251 opened Feb 23, 2026 by Kaylebor Loading…
4
fix(llama): respect NODE_LLAMA_CPP_GPU override
#250 opened Feb 23, 2026 by Kaylebor Loading…
1
fix: try Vulkan before CUDA, iterate on failure instead of falling back to CPU
#246 opened Feb 22, 2026 by johnmcmullan Loading…
feat: add Jina Embeddings v5 text-nano and text-small as alternative models
#245 opened Feb 22, 2026 by hanxiao Loading…
Better GPU backend detection + flake variants
#244 opened Feb 22, 2026 by reedriley Loading…
fix: use getLlamaGpuTypes("supported") to detect actual GPU availability
#243 opened Feb 21, 2026 by DanieleSalatti Loading…
1
feat(query): add --explain score traces for hybrid retrieval
#242 opened Feb 21, 2026 by vyalamar Loading…
fix(#233): improve multi-collection search filtering
#241 opened Feb 21, 2026 by ambicuity Loading…
1
3
fix(gpu): try all available backends before falling back to CPU
#240 opened Feb 21, 2026 by haddadrm Loading…
1
fix(llm): try all available GPU types before falling back to CPU
#237 opened Feb 21, 2026 by JonBasse Loading…
1
fix: Windows homedir, multi-session MCP, GPU override, collection routing
#235 opened Feb 20, 2026 by kenaroik Loading…
7 tasks done
fix(llm): prevent reranker context overflow on large chunks
#234 opened Feb 20, 2026 by kevin-courbet Loading…
fix(mcp): add --host flag to HTTP server bind address
#232 opened Feb 20, 2026 by kleddbot Loading…
1
1
fix(cli): suppress progress bars when not TTY
#230 opened Feb 20, 2026 by dgilperez Loading…
fix(cli): prevent parser breakage on empty results across output formats
#228 opened Feb 19, 2026 by amsminn Loading…
feat(llm): support QMD_GEN_MODEL env var for query expansion model override
#226 opened Feb 19, 2026 by OmerFarukOruc Loading…
1
fix(package.json): correct Windows sqlite-vec package name + add linux-arm64
#225 opened Feb 19, 2026 by ilepn Loading…
4 tasks
1
Fix multi-collection filtering in search/query/vsearch
#218 opened Feb 18, 2026 by 1kuna Loading…
Added filename support for +-=[], for example as might be used in +=.…
#216 opened Feb 18, 2026 by Asher- Loading…
feat(llm): add API backend support with backend-aware session routing
#204 opened Feb 17, 2026 by marcinbogdanski • Draft
3
ProTip! What’s not been updated in a month: updated:<2026-01-27.