| pr |
1.00 |
docs: update Screenpipe URL (repo renamed from mediar-ai to |
|
Explicitly states update was by an autom |
2026-06-25 |
| pr |
1.00 |
llm: keep projector offload enabled for integrated ROCm GPUs |
|
PR body explicitly mentions AI collabora |
2026-06-16 |
| pr |
1.00 |
readme: add nolock to Code Editors & Development section |
|
PR body explicitly mentions AI collabora |
2026-06-23 |
| pr |
1.00 |
README: add AFK community integration |
|
Commit trailer: Co-Authored-By: AFK usin |
2026-06-20 |
| pr |
0.40 |
feat: improve CLI navigation, implement atomic manifest writ |
|
Slightly formal, but detailed and uses i |
2026-06-21 |
| pr |
0.20 |
fix(cli): abort interactive mode with error when stdout is r |
|
Direct, problem-focused, and domain-spec |
2026-06-21 |
| pr |
0.20 |
app/ui: allow pasting images and files from the clipboard in |
|
Proper technical summary; domain terms a |
2026-04-13 |
| pr |
0.20 |
server: default gemma4 thinking to off |
|
Precise, technical, with referenced issu |
2026-06-21 |
| pr |
0.15 |
Add num_cpu_moe option to keep MoE expert tensors on the CPU |
|
Structured technical style, minimal free |
2026-06-12 |
| pr |
0.15 |
server: expose llama-server slot API |
|
Domain detail, technical explanations; n |
2026-06-15 |
| commit |
0.10 |
llm: decouple prompt caching from context shift (#16639) |
|
Direct, domain-specific language; no AI |
2026-06-11 |
| commit |
0.10 |
mlxrunner: harden linear/embedding layers against over-promo |
|
Concise technical phrasing and jargon; h |
2026-06-11 |
| commit |
0.10 |
mlx: "requires" in modelfile is being ignored for mlx based |
|
Technical, concise; just slightly formal |
2026-06-03 |
| commit |
0.10 |
log template details to aid troubleshooting (#16403) |
|
Concise technical explanation, natural f |
2026-06-01 |
| pr |
0.10 |
windows: add install.ps1 cache modes |
|
Slightly more formal but includes domain |
2026-06-25 |
| pr |
0.10 |
launch: auto-install opencode when missing |
|
Follows template, but concise technical |
2026-06-18 |
| pr |
0.10 |
launch: Add VS Code extension launch flow |
|
Uses domain-specific language and inform |
2026-06-09 |
| pr |
0.10 |
llama: add sm_86 architecture to cuda_v13_windows preset |
|
Highly domain-specific, detailed with hu |
2026-06-20 |
| pr |
0.10 |
Add Atlarix to Code Editors & Development integrations |
|
Domain knowledge, concise phrasing, and |
2026-04-24 |
| pr |
0.10 |
create: route quantize through MLX worker thread |
|
Domain-specific detail and user reports; |
2026-05-10 |
| pr |
0.10 |
ml/backend/ggml: add experimental SYCL backend support |
|
Technical language, proposals, and human |
2026-05-07 |
| pr |
0.10 |
fix(cmd): prevent ANSI escape sequences in piped output |
|
Specific debugging info and typical deve |
2026-06-22 |
| pr |
0.10 |
fix(server): support nested model names in v1/models/ endpoi |
|
Uses template but changes are clear and |
2026-01-14 |
| pr |
0.10 |
env: expose user-visible OLLAMA_NUM_THREADS override |
|
Technical and concise user-facing change |
2026-05-20 |
| pr |
0.10 |
ggml: Fix PowerPC build and enable MMA Optimizations |
|
Detailed architecture-specific breakdown |
2025-12-22 |
| pr |
0.10 |
feat: add tokenization api for ollama |
|
In-house API description, terse and tech |
2026-06-19 |
| pr |
0.10 |
docs: show how to disable OpenAI reasoning |
|
Clear, domain-specific doc update, human |
2026-06-22 |
| pr |
0.10 |
Add CapyBro to Community Integrations (Productivity & Apps) |
|
Very direct and human in style; no AI ha |
2026-06-16 |
| pr |
0.10 |
ui: add local-only model filter |
|
Standard feature description; technical, |
2026-06-21 |
| pr |
0.10 |
cmd/launch: add support for glm-5.2 cloud model |
|
Direct, domain-specific, and concise in |
2026-06-14 |
| pr |
0.10 |
docs: clarify OpenAI-compatible request fields |
|
Concise, domain-specific, template style |
2026-06-21 |
| pr |
0.10 |
Recover qwen tool calls when the tool-call xml is malformed |
|
Technical, includes errors & code; natur |
2026-06-21 |
| pr |
0.10 |
Don't write word-wrap escape sequences when stdout is not a |
|
Bug report and fix, typical structured h |
2026-06-21 |
| pr |
0.10 |
docs: fix stale compatibility examples |
|
Routine documentation update in template |
2026-06-21 |
| pr |
0.10 |
Show the full command in the experimental agent tool-call di |
|
Free-form explanation, uses informal ton |
2026-06-21 |
| pr |
0.10 |
Fix image path detection when a parent directory ends in an |
|
Technical bug narrative, shows specifici |
2026-06-21 |
| pr |
0.10 |
model/parsers: tolerate qwen tool-call format drift (qwen3.6 |
|
Detailed bug diagnosis and fix, domain-s |
2026-06-01 |
| pr |
0.10 |
server: Add OLLAMA_NO_MMAP to disable mmap globally |
|
Straightforward PR, minimal formalism, c |
2024-09-18 |
| pr |
0.10 |
Add CapyBro to Community Integrations (Productivity & Apps) |
|
Very direct and human in style; no AI ha |
2026-06-19 |
| pr |
0.10 |
docs: add nxusKit to community integrations |
|
Standard README update, minimal explanat |
2026-05-07 |
| commit |
0.05 |
launch: auto-install opencode when missing (#16806) |
|
Terse, domain-specific commit message; h |
2026-06-19 |
| commit |
0.05 |
launch: auto-install Claude Code (#16802) |
|
Concise changelog phrasing; lacks AI sty |
2026-06-19 |
| commit |
0.05 |
server: context shift for context windows larger than 8k, ad |
|
Terse commit message, human style, no AI |
2026-06-15 |
| commit |
0.05 |
model: update lfm2 parser/renderer for optional thinking (#1 |
|
Brief technical wording, lacks AI-style |
2026-06-15 |
| commit |
0.05 |
llama: update llama.cpp to b9637 (#16609) |
|
Direct update message, domain-specific, |
2026-06-15 |
| commit |
0.05 |
mlx: fix reported information in `ollama show` (#16289) |
|
Concise changelog with technical details |
2026-05-24 |
| commit |
0.05 |
launch: enriched model inventory (#16230) |
|
Brief, technical with domain-specific ph |
2026-05-21 |
| pr |
0.05 |
darwin: improve free memory reporting |
|
Informal, technical, includes log output |
2025-10-28 |
| pr |
0.05 |
reduce default server log verbosity |
|
Terse, technical, includes inline develo |
2026-06-25 |
| pr |
0.05 |
feat: opt-in slot KV save/restore via OLLAMA_SLOT_SAVE_PATH |
|
Concise, informal, specific technical re |
2026-06-21 |
| pr |
0.05 |
launch/codex: detect model drift when Codex App UI switches |
|
Detailed technical analysis, domain-spec |
2026-06-22 |
| pr |
0.05 |
mlxrunner: unify and tune speculative decoding |
|
Domain expertise with abbreviations, inf |
2026-06-18 |
| pr |
0.05 |
docs: update development.md with clarifying build steps for |
|
Brief, informal, includes personal exper |
2026-06-22 |
| pr |
0.05 |
discover: fix inverted iGPU/dGPU Vulkan classification on Wi |
|
Technical, specific issue reference, hum |
2026-06-11 |
| pr |
0.05 |
Honor model generation defaults |
|
Technical content, review comments shown |
2026-06-03 |
| pr |
0.05 |
server: support importing split GGUF models with multiple FR |
|
Technical language, bullet points, handl |
2026-05-19 |
| pr |
0.05 |
responses: support namespace tool calls |
|
Concise technical explanation, domain ja |
2026-05-22 |
| pr |
0.05 |
docs: update glm references to glm-5.2 |
|
Short, domain-focused update, typical hu |
2026-06-22 |
| pr |
0.05 |
mlx: disable unsafe prompt cache restore |
|
Issue-focused, technical summary and rat |
2026-06-22 |
| pr |
0.05 |
Add Bodega One to Community Integrations |
|
Very brief, domain-savvy, zero AI hallma |
2026-06-22 |
| pr |
0.05 |
server: cancel pull on client disconnect |
|
Terse, domain-specific, informal bullet |
2026-04-29 |
| pr |
0.05 |
llm: disable llama fit for Gemma4 on limited VRAM |
|
Concise technical summary; domain jargon |
2026-06-20 |
| pr |
0.05 |
fix: auto-disable thinking for audio inputs |
|
Technical, detailed, informal; contains |
2026-06-06 |
| pr |
0.05 |
cmd: extract complete file paths with dotted directories |
|
Technical language and details; human-wr |
2026-06-15 |
| pr |
0.05 |
openai: forward num_ctx to options in OpenAI-compatible endp |
|
Detailed, domain-specific, structured ex |
2026-06-20 |
| pr |
0.05 |
openai: pass through chat truncate option |
|
Technical, concise, uses domain-specific |
2026-06-20 |
| pr |
0.05 |
x/mlxrunner: support the diffusion-gemma architecture (MLX/s |
|
Jargon and references; informal summary; |
2026-06-14 |
| pr |
0.05 |
win: Image Generation support |
|
Concise, technical summary, includes rel |
2026-01-21 |
| pr |
0.05 |
cmd/interactive: show /list in usage message |
|
Very terse, informal description; unmist |
2026-06-05 |
| commit |
0.01 |
server: remove duplicate template parsing (#16287) |
|
Very terse, typical human commit message |
2026-05-24 |
| commit |
0.00 |
launch: update hermes install urls to official (#16913) |
|
Concise, technical commit, typical human |
2026-06-25 |
| commit |
0.00 |
fix capability grid dark mode style (#16907) |
|
Terse bugfix commit, minimal context, cl |
2026-06-25 |
| commit |
0.00 |
CUDA: require driver 550 or newer for v12 (#16895) |
|
Contains technical jargon, details, huma |
2026-06-25 |
| commit |
0.00 |
docs: redesign coding integration docs (#16808) |
|
Very brief, typical for docs update comm |
2026-06-25 |
| commit |
0.00 |
llama.cpp version update (#16548) |
|
Sparse, standard technical commit title, |
2026-06-24 |
| commit |
0.00 |
jetson: add CC 87 for CUDA v13 (#16628) |
|
Concise title and brief technical explan |
2026-06-24 |
| commit |
0.00 |
server: align generate with native chat templates (#16878) |
|
Technical jargon, informal phrasing, no |
2026-06-24 |
| commit |
0.00 |
docs: redesign docs landing and integrations overview (#1680 |
|
Standard docs commit message with co-aut |
2026-06-24 |
| commit |
0.00 |
llm: fix ollama ps double-counting mmap'd weights on partial |
|
Detailed technical explanation, normal i |
2026-06-24 |
| commit |
0.00 |
mlx: update and fix CUDA JIT packaging (#16871) |
|
Technical, specific, human-like explanat |
2026-06-24 |
| commit |
0.00 |
llm: use host Vulkan loader on Windows (#16869) |
|
Short technical summary, human phrasing. |
2026-06-24 |
| commit |
0.00 |
llama: default qwen2.5vl window attention metadata (#16868) |
|
Detailed domain-specific description, in |
2026-06-24 |
| commit |
0.00 |
llm: preserve generation headroom for shifted prompts (#1685 |
|
Brief message, touches on context, no AI |
2026-06-23 |
| commit |
0.00 |
docs: document max think level (#16877) |
|
Concise, uses common docs commit format, |
2026-06-23 |
| commit |
0.00 |
llm: size mmproj offload by projector memory (#16866) |
|
Technical, domain acronyms, no generic o |
2026-06-23 |
| commit |
0.00 |
llama: add sm_86 architecture to cuda_v13_windows preset (#1 |
|
Detailed technical explanation, signed b |
2026-06-23 |
| commit |
0.00 |
launch/codex: detect model drift when Codex App UI switches |
|
Concise, technical summary with context- |
2026-06-22 |
| commit |
0.00 |
mlxrunner: choose the speculative draft length to maximize t |
|
Uses technical abbreviations and concise |
2026-06-10 |
| commit |
0.00 |
mlxrunner: resolve each speculative round in one host sync |
|
Efficient phrasing and technical descrip |
2026-06-11 |
| commit |
0.00 |
mlxrunner: run one target forward per MTP decode step |
|
Terse, technical, and uses inline explan |
2026-06-10 |
| commit |
0.00 |
mlxrunner: apply in-flight drafts to proposal penalty histor |
|
Precise technical explanation, abbreviat |
2026-06-12 |
| commit |
0.00 |
mlxrunner: support draft heads that maintain draft caches |
|
Domain-specific language, clear technica |
2026-06-10 |
| commit |
0.00 |
mlxrunner: host speculative decoding in the text generation |
|
Direct technical restructuring, no boile |
2026-06-09 |
| commit |
0.00 |
mlxrunner: unify the MTP decode paths |
|
Concise explanation of code changes, ver |
2026-06-02 |
| commit |
0.00 |
discover: fix inverted iGPU/dGPU Vulkan classification on Wi |
|
Specific bug description, technical deta |
2026-06-22 |
| commit |
0.00 |
launch: add thinking capability detection to opencode (#1543 |
|
Commit message is terse and technical wi |
2026-06-18 |
| commit |
0.00 |
ci: pin darwin release xcode (#16788) |
|
Terse commit message, no AI signals. |
2026-06-17 |
| commit |
0.00 |
llama: update llama.cpp to b9672 (#16775) |
|
Brief update, domain specific, human-lik |
2026-06-17 |
| commit |
0.00 |
models: add cohere2_moe (Command A / North) to the MLX engin |
|
Includes jargon, succinct, typical human |
2026-06-17 |
| commit |
0.00 |
llm: context shift allow shiftable prompts (#16764) |
|
Terse commit title, zero AI signals. |
2026-06-16 |
| commit |
0.00 |
integration: look for the "hf" tool in integration tests (#1 |
|
Concise, technical, no AI hallmarks. |
2026-06-16 |
| commit |
0.00 |
launch: Fix launch provider drift (#16683) |
|
Brief message with domain jargon and inf |
2026-06-12 |
| commit |
0.00 |
mlxrunner: record committed MTP drafts before streaming them |
|
Technical, terse, contains domain-specif |
2026-06-01 |
| commit |
0.00 |
mlxrunner: capture prefill snapshots across the forward |
|
Contains domain-specific terms and natur |
2026-05-29 |
| commit |
0.00 |
mlxrunner: drive MTP speculation through cache snapshots |
|
Casual engineering tone, with technical |
2026-05-29 |
| commit |
0.00 |
nn/recurrent: return per-boundary states from the gated-delt |
|
Technical with specific kernel/layer det |
2026-05-29 |
| commit |
0.00 |
mlxrunner/cache: split KVCache and RotatingKVCache into thei |
|
File reorganization with clear, brief en |
2026-05-29 |
| commit |
0.00 |
mlxthread: preserve the original stack when worker work pani |
|
Precise, technical description with natu |
2026-05-27 |
| commit |
0.00 |
docs: omp (#16552) |
|
Terse, domain-specific commit; no AI sig |
2026-06-08 |
| commit |
0.00 |
docs: hermes desktop (#16549) |
|
Minimal content; no AI stylistic feature |
2026-06-08 |
| commit |
0.00 |
docs: update docs examples to use Gemma 4 instead of Gemma 3 |
|
Standard technical commit message, no AI |
2026-06-07 |
| commit |
0.00 |
Add AGENTS.md and CLAUDE.md to root repository (#16604) |
|
Concise subject, no AI signals present. |
2026-06-07 |
| commit |
0.00 |
docs: describe llama.cpp update process (#16603) |
|
Standard technical commit summary, human |
2026-06-07 |
| commit |
0.00 |
openai: align models list with tags (#16556) |
|
Concise commit message, domain shorthand |
2026-06-06 |
| commit |
0.00 |
launch: use native Windows Hermes config path (#16558) |
|
Brief technical message, human style, no |
2026-06-06 |
| commit |
0.00 |
docs: update Zod example to use native toJSONSchema (#14746) |
|
Short technical message, human, includes |
2026-06-05 |
| commit |
0.00 |
launch: oh-my-pi (#16410) |
|
Commit message is brief and typical of h |
2026-06-05 |
| commit |
0.00 |
mlx: allow the embedding layer to use the nvfp4 global scale |
|
Technical title, no signs of AI phrasing |
2026-06-05 |
| commit |
0.00 |
docs: add cloud model retirement (#16528) |
|
Minimal changelog, concise and domain-sp |
2026-06-04 |
| commit |
0.00 |
launch: hermes-desktop app (#16516) |
|
Direct and brief, uses domain language a |
2026-06-04 |
| commit |
0.00 |
llama.cpp version update (#16511) |
|
Detailed but technical, with issue refer |
2026-06-04 |
| commit |
0.00 |
integrations: hermes windows install (#16487) |
|
Very brief changelog, standard human com |
2026-06-04 |
| commit |
0.00 |
docs: add Cline CLI integration doc (#16341) |
|
Very short, docs update typical for huma |
2026-06-04 |
| commit |
0.00 |
llama-server: fix gemma4 patch wiring (#16477) |
|
Terse technical commit message with spec |
2026-06-03 |
| commit |
0.00 |
launch: migrate pi (#16213) |
|
Brief, informal, just a technical migrat |
2026-06-03 |
| commit |
0.00 |
llama-server: allow GPU offload for projectors (#16473) |
|
Contains jargon and specific details; in |
2026-06-03 |
| commit |
0.00 |
server: classify mmproj GGUFs as projector layers (#16472) |
|
Direct technical commit; no AI signals. |
2026-06-03 |
| commit |
0.00 |
launch: clean legacy codex profile before launch (#16467) |
|
Short, domain-specific; no sign of AI ge |
2026-06-03 |
| commit |
0.00 |
Kill llama-server during Windows cleanup (#16458) |
|
Clear, specific description with informa |
2026-06-03 |
| commit |
0.00 |
llama.cpp version update (#16463) |
|
Technical changelog; concise and domain- |
2026-06-03 |
| commit |
0.00 |
models: add support for gemma4-12b (#16457) |
|
Very terse and standard technical commit |
2026-06-03 |
| commit |
0.00 |
fix laguna patch build breakage (#16445) |
|
Technical fix with domain details and te |
2026-06-02 |
| commit |
0.00 |
llm: ignore llama-server SSE ping comments (#16443) |
|
Contains domain jargon, informal explana |
2026-06-02 |
| commit |
0.00 |
docs: configure hermes desktop app (#16440) |
|
Minimal template-driven docs commit, no |
2026-06-02 |
| commit |
0.00 |
llama: add laguna (poolside) arch via a llama.cpp patch unde |
|
Contains technical specifics and human c |
2026-06-02 |
| commit |
0.00 |
launch: isolate Codex launch configuration (#16437) |
|
Short, domain-specific commit message; n |
2026-06-02 |
| commit |
0.00 |
llama.cpp version update (#16426) |
|
Generic update message, but no AI marker |
2026-06-02 |
| commit |
0.00 |
More harden app markdown URL handling (#16436) |
|
Domain phrase, human-typical wording for |
2026-06-02 |
| commit |
0.00 |
llm: detect llama-server load stalls from output (#16427) |
|
Complex technical description with jargo |
2026-06-02 |
| commit |
0.00 |
discover: allow Radeon 8060S iGPU by default (#16429) |
|
Detailed technical explanation, issue re |
2026-06-02 |
| commit |
0.00 |
Harden app markdown URL handling (#16380) |
|
Human-style commit with domain-specific |
2026-06-02 |
| commit |
0.00 |
llm: include cached prompt tokens in llama-server counts (#1 |
|
Contains technical jargon and concise ex |
2026-06-02 |
| commit |
0.00 |
launch: fix opencode local model limits (#16425) |
|
Technical language, no signs of AI-style |
2026-06-02 |
| commit |
0.00 |
cmd/launch: add Qwen code integration (#15900) |
|
Minimal message, no AI indicators. |
2026-06-01 |
| commit |
0.00 |
feat(launch): show and auto-install Cline CLI (#16402) |
|
No free text or AI hallmarks, only chang |
2026-06-01 |
| commit |
0.00 |
launch: migrate Codex config (#16397) |
|
Brief commit summary without AI characte |
2026-06-01 |
| commit |
0.00 |
cmd/launch: fix configure cline ollama provider via provider |
|
Human-style technical commit; no AI sign |
2026-06-01 |
| commit |
0.00 |
launch: avoid legacy Codex App profiles (#16364) |
|
Brief, technical; co-author is human, no |
2026-06-01 |
| commit |
0.00 |
llama-server followups (#16353) |
|
Informal, domain-specific, natural human |
2026-06-01 |
| commit |
0.00 |
convert: fixes for qwen3next model conversion (#16354) |
|
Technical bulleted list, domain-specific |
2026-06-01 |
| commit |
0.00 |
model: improvements to laguna-xs.2 parser/renderer (#16362) |
|
— |
2026-05-31 |
| commit |
0.00 |
llama: handle Gemma 4 and LFM2 BOS override in llama server |
|
— |
2026-05-31 |
| commit |
0.00 |
mlx: fix dev mode search path (#16355) |
|
— |
2026-05-29 |
| commit |
0.00 |
runner: Remove CGO engines, use llama-server exclusively for |
|
— |
2026-05-29 |
| commit |
0.00 |
mlxrunner: keep gated-delta recurrent state in float32 |
|
Dense technical detail and jargon, clear |
2026-05-20 |
| commit |
0.00 |
create: read draft architecture from its config.json |
|
Succinct technical summary with domain-s |
2026-05-20 |
| commit |
0.00 |
mlxrunner: move YaRN RoPE helpers into x/models/nn |
|
Brief, direct, and domain-specific refac |
2026-05-20 |
| commit |
0.00 |
Revert "mlxrunner: add DFlash speculative decoding (#16134)" |
|
Classic human rollback PR, with informal |
2026-05-20 |
| pr |
0.00 |
server: add cached eval metric to response |
|
Uses project terms and technical languag |
2026-06-25 |
| pr |
0.00 |
launch: update hermes install urls to official |
|
Direct, domain-specific, website update, |
2026-06-25 |
| pr |
0.00 |
readme: add OpenAgentic to Frameworks & Agents |
|
Rich technical jargon, typical README co |
2026-06-25 |
| pr |
0.00 |
fix cuda toolkit lookup and parallel |
|
Technical explanation, project structure |
2026-06-07 |
| pr |
0.00 |
agent: ollama agent loop |
|
Domain detail, technical lists, no AI-st |
2026-06-15 |
| pr |
0.00 |
windows: use install.ps1 for app upgrades |
|
Details Windows app process, clear devel |
2026-06-25 |
| pr |
0.00 |
llama-server: prepare to remove compatibility patch with man |
|
Long, technical, with domain-specific te |
2026-06-07 |
| pr |
0.00 |
launch: hermes desktop in the background |
|
Direct, technical, and informal with cle |
2026-06-25 |
| pr |
0.00 |
docs: update vscode docs |
|
Empty description; no AI signals present |
2026-06-25 |
| pr |
0.00 |
launch: check for min version for hermes desktop |
|
Technical detail, specific references, s |
2026-06-25 |
| pr |
0.00 |
sched: align placement reserve with llama fit target |
|
Terse, domain-specific language and reas |
2026-06-24 |
| pr |
0.00 |
fix: reduce llama-server default logging verbosity (#16897) |
|
Technical breakdown with bullet points a |
2026-06-25 |
| pr |
0.00 |
docs: update hermes docs |
|
Empty description; no content to evaluat |
2026-06-25 |
| pr |
0.00 |
docs: fix capability grid dark mode style |
|
Empty description; no content to evaluat |
2026-06-25 |
| pr |
0.00 |
server: fix unified Gemma4 vision support |
|
Highly detailed, technical, with specifi |
2026-06-23 |
| pr |
0.00 |
CUDA: require driver 550 or newer for v12 |
|
Brief, uses domain-specific language and |
2026-06-25 |
| pr |
0.00 |
docs: Redesign OpenClaw integration page |
|
No free text, only a title; no evidence |
2026-06-24 |
| pr |
0.00 |
docs: redesign coding integration docs |
|
No real content; simply a placeholder co |
2026-06-18 |
| pr |
0.00 |
discover: allow gfx1150 (RDNA 3.5) integrated GPU by default |
|
Root-cause focused, uses domain abbrevia |
2026-06-13 |
| pr |
0.00 |
mlx: route fast quantized matmul on CUDA |
|
Domain jargon, informal tone, and technc |
2026-06-25 |
| pr |
0.00 |
llama.cpp version update |
|
Very brief, title-only; human-written st |
2026-06-05 |
| pr |
0.00 |
jetson: add CC 87 for CUDA v13 |
|
Uses domain jargon and specific details; |
2026-06-08 |
| pr |
0.00 |
server: align generate with native chat templates |
|
Technical with domain abbreviations and |
2026-06-23 |
| pr |
0.00 |
docs: redesign docs landing and integrations overview |
|
Short, non-formal, lacks AI indicators. |
2026-06-18 |
| pr |
0.00 |
llm: fix ollama ps double-counting mmap'd weights on partial |
|
Detailed technical bug description, doma |
2026-06-13 |
| pr |
0.00 |
mlx: update and fix CUDA JIT packaging |
|
Detailed, technical, and context-specifi |
2026-06-23 |
| pr |
0.00 |
llm: use host Vulkan loader on Windows |
|
Terse, technical, and includes a human r |
2026-06-23 |
| pr |
0.00 |
llama: default qwen2.5vl window attention metadata |
|
Brief, precise problem description with |
2026-06-22 |
| pr |
0.00 |
server: grow embedding batch for long inputs |
|
Concise technical explanation with domai |
2026-06-24 |
| pr |
0.00 |
fix: add verbose flag to launch command |
|
Follows issue template, includes self-do |
2026-06-24 |
| pr |
0.00 |
fix: disable word wrap for redirected run output |
|
Uses domain-specific tests and abbreviat |
2026-06-24 |
| pr |
0.00 |
Update install.sh - add status for url |
|
Direct, concise, and domain-specific; no |
2026-06-24 |
| pr |
0.00 |
fix(readline): support Ctrl+Left/Right word navigation |
|
Technical language with abbreviations an |
2026-06-20 |
| pr |
0.00 |
llm: size-aware mmproj offload instead of blanket 10 GiB VRA |
|
Contains domain jargon, informal tone, n |
2026-06-06 |
| pr |
0.00 |
llm: preserve generation headroom for shifted prompts |
|
Structured summary with technical nuance |
2026-06-22 |
| pr |
0.00 |
docs: document max think level |
|
Domain-specific, test logs, and concise |
2026-06-23 |
| pr |
0.00 |
llm: size mmproj offload by projector memory |
|
Uses jargon, references issues, and is c |
2026-06-22 |
| pr |
0.00 |
Fix port typo: cmd_test.go |
|
Extremely terse; minimal, direct changel |
2026-03-15 |
| pr |
0.00 |
Claude/sleepy feynman yluryv |
|
Short, informal text fragment; no typica |
2026-06-23 |
| pr |
0.00 |
docs: mark Logprobs as supported in OpenAI compatibility |
|
Specific, precise, and technical explana |
2026-06-22 |
| pr |
0.00 |
Respond with text/event-stream (SSE) if requested |
|
Brief, precise, and informal; typical of |
2025-07-30 |
| pr |
0.00 |
launch: auto-install Claude Code |
|
Technical, detailed PR, no AI-style poli |
2026-06-18 |
