| commit |
1.00 |
fix(docs): correct typos found during code review (#17579) |
|
Commit message contains explicit AI assi |
2026-08-31 |
| commit |
1.00 |
cmake: make external compat patches idempotent (#17948) |
|
Commit message contains explicit AI assi |
2026-08-26 |
| pr |
1.00 |
fix(parsers/qwen3coder): recover bare tool ca |
|
Explicitly states the change was generat |
2026-06-12 |
| pr |
1.00 |
feat: Add GraniteForCausalLM support in experimental models |
|
Explicitly documents development with Cl |
2026-08-24 |
| pr |
1.00 |
openai: accept agent_message input items |
|
Explicitly states the contribution was p |
2026-09-07 |
| pr |
1.00 |
llm: filter per-request llama-server logs unless debug is en |
|
Explicitly states that generative AI ass |
2026-08-21 |
| pr |
1.00 |
server: add experimental prefill cache persistence across ru |
|
Explicitly states the work was developed |
2026-08-23 |
| pr |
1.00 |
docs: show actual JSON array output for embeddings example |
|
Explicitly states the PR was prepared wi |
2026-09-08 |
| pr |
1.00 |
fs/gguf: fix integer overflow in TensorInfo.NumValues/NumByt |
|
Explicitly identifies the text as genera |
2026-09-07 |
| pr |
0.95 |
Enhance Ollama integration with n8n workflows, ComfyUI examp |
|
Copilot review structure and generic ove |
2026-09-08 |
| pr |
0.92 |
Feature/complete model signing |
|
Generic, overly polished security pitch |
2025-07-30 |
| pr |
0.78 |
feat(backend): Implement native Intel SYCL (oneAPI) runner p |
|
Highly polished, promotional wording and |
2026-09-09 |
| pr |
0.72 |
docs(integrations): add TealKit agent integration and docs |
|
Polished promotional framing and uniform |
2026-09-10 |
| pr |
0.22 |
api: accept nested object required schemas |
|
Detailed compatibility scope and test li |
2026-08-30 |
| pr |
0.22 |
llama.cpp: version bump b10829 for support Spark X2.5 model |
|
Mostly technical, but the model descript |
2026-09-07 |
| pr |
0.18 |
fix(app): skip sidebar animation on initial load |
|
Polished generic summary structure is mi |
2026-01-16 |
| pr |
0.18 |
app: hide macOS app after closing its window |
|
Structured technical summary with concre |
2026-08-04 |
| pr |
0.08 |
launch: add Atomic Agent integration |
|
Detailed integration steps and live-run |
2026-08-25 |
| pr |
0.08 |
fix(deps): bump golang.org/x/image to patch WebP decoder DoS |
|
Highly specific security and dependency |
2026-09-10 |
| pr |
0.08 |
model/parsers: preserve quoted qwen3 tool delimiters |
|
Specific parser behavior, edge cases, an |
2026-09-09 |
| pr |
0.07 |
proxy: normalize namespaced commands in Full Access |
|
Concise but specific description of name |
2026-09-09 |
| pr |
0.06 |
app: configure allowed browser origins in settings |
|
Detailed UI and migration specifics are |
2026-09-08 |
| pr |
0.06 |
docs: add Harbor to community integrations |
|
Brief, generic documentation contributio |
2026-09-07 |
| pr |
0.05 |
app: refresh Apps layout and command copy feedback |
|
Detailed validation results and platform |
2026-09-10 |
| pr |
0.05 |
x/mlxrunner/mlx: report missing symbols lazily instead of pr |
|
Detailed technical report; included bot |
2026-09-09 |
| pr |
0.04 |
llm: raise token repeat limit to 100 and return error instea |
|
Informal wording, typos, and concrete OC |
2026-09-10 |
| pr |
0.04 |
create: add server-side MLX imports and drop GGUF conversion |
|
Specific implementation scope and cleanu |
2026-03-19 |
| pr |
0.04 |
server: extract GGUF metadata and unify capabilities |
|
Specific cache behavior, timings, and an |
2026-08-18 |
| pr |
0.04 |
proxy: preserve Codex stream failures |
|
Concise domain-specific description with |
2026-09-09 |
| pr |
0.04 |
openai: accept plaintext-labeled Codex agent messages |
|
Brief, slightly informal description wit |
2026-09-08 |
| pr |
0.04 |
anthropic: output_config.effort without a thinking block sho |
|
Detailed API behavior and client evidenc |
2026-09-08 |
| pr |
0.04 |
app: open Codex by default for Ollama launches |
|
Concise implementation and testing detai |
2026-09-08 |
| pr |
0.04 |
Add Talos as an `ollama launch` integration |
|
Detailed implementation notes are techni |
2026-08-28 |
| pr |
0.04 |
llm: skip --spec-draft-backend-sampling in tensor split mode |
|
Detailed performance measurements and im |
2026-09-08 |
| pr |
0.04 |
server: add metrics endpoint |
|
Detailed technical changelog with reposi |
2026-07-01 |
| pr |
0.04 |
server: reload when two tags share a blob but need different |
|
Highly specific debugging narrative with |
2026-09-07 |
| commit |
0.03 |
llama.cpp: version bump b10729 (#18160) |
|
Terse, repository-specific changelog wit |
2026-09-01 |
| commit |
0.03 |
Honor model generation defaults (#16471) |
|
Specific behavior, metadata sources, and |
2026-09-01 |
| commit |
0.03 |
app: claude model management (#17915) |
|
Terse, conventional commit title with no |
2026-08-21 |
| commit |
0.03 |
app: add Connect your apps experience (#17900) |
|
Terse, conventional commit title with no |
2026-08-21 |
| commit |
0.03 |
mlx: fix mac assumptions on linux/windows (#17898) |
|
Concise title and specific informal expl |
2026-08-20 |
| commit |
0.03 |
server: don't wedge chat and generate on a mid-stream parser |
|
Specific concurrency failure analysis an |
2026-08-19 |
| pr |
0.03 |
mlx: scope array lifetimes instead of pinning and sweeping |
|
Highly specific memory-management detail |
2026-09-08 |
| pr |
0.03 |
llm: keep gemma3n projector off the CPU |
|
Concise, domain-specific bug description |
2026-09-10 |
| pr |
0.03 |
mlxrunner: check system free memory and wait for evicted run |
|
Concrete scheduler and process-lifecycle |
2026-09-09 |
| pr |
0.03 |
proxy: let Claude Desktop use a model's full context window |
|
Detailed product-specific behavior and e |
2026-09-10 |
| pr |
0.03 |
go.mod: bump golang.org/x/image and golang.org/x/crypto to p |
|
Detailed vulnerability reachability anal |
2026-07-09 |
| pr |
0.03 |
model/renderers: always render the qwen3.5 assistant think b |
|
Detailed, domain-specific performance an |
2026-09-10 |
| pr |
0.03 |
openai: support standalone named function outputs |
|
Detailed protocol and compaction specifi |
2026-09-09 |
| pr |
0.03 |
openai: preserve response text alongside tool calls |
|
Specific API, streaming, and test detail |
2026-09-09 |
| pr |
0.03 |
video: accept video input on macOS |
|
Specific issue references, implementatio |
2026-09-01 |
| pr |
0.03 |
openai: expose tools loaded by client tool search |
|
Detailed, test-specific technical explan |
2026-09-08 |
| pr |
0.03 |
app: add a first-use ChatGPT connection intro |
|
Detailed, domain-specific change descrip |
2026-09-08 |
| pr |
0.03 |
mlxrunner: support Qwen static YaRN contexts |
|
Specific model, metadata, tests, and com |
2026-09-05 |
| pr |
0.03 |
mlxrunner: honor explicit context without overriding soft si |
|
Specific MLX behavior, issue references, |
2026-09-07 |
| pr |
0.03 |
model/parsers: preserve multiline functiongemma tool argumen |
|
Concrete parser behavior, examples, and |
2026-09-08 |
| pr |
0.03 |
app: preserve Codex configuration across host changes |
|
Brief, specific description of endpoint |
2026-09-05 |
| pr |
0.03 |
template: preserve developer instructions in Go templates |
|
Specific regressions, credits, environme |
2026-09-08 |
| pr |
0.03 |
gemma4: a tool call can open before the thinking channel is |
|
Detailed parser behavior, tests, and dom |
2026-09-08 |
| pr |
0.03 |
gemma4: do not answer with a channel name the parser was cut |
|
Specific bug reproduction, streaming beh |
2026-08-08 |
| pr |
0.03 |
agent/tools: confine absolute read paths to the working dire |
|
Highly specific security analysis and im |
2026-08-26 |
| commit |
0.02 |
server: extract GGUF metadata and unify capabilities (#17858 |
|
Technical changelog includes concrete pa |
2026-09-10 |
| commit |
0.02 |
ci: rebuild MLX macOS test payloads the release can't supply |
|
Highly specific CI behavior and terse ph |
2026-09-03 |
| commit |
0.02 |
Report cached prompt tokens (#17943) |
|
Structured changelog with concrete API a |
2026-09-02 |
| commit |
0.02 |
launch: respect OLLAMA_HOST when configuring Pi (#18039) |
|
Specific technical diagnosis and behavio |
2026-08-26 |
| commit |
0.02 |
MLX: Qwen3.8 Flash Next support (#18032) |
|
Terse feature note and review reference, |
2026-08-26 |
| commit |
0.02 |
app: improve desktop integration responsiveness (#17973) |
|
Multiple concise, technically specific c |
2026-08-24 |
| commit |
0.02 |
app: fix desktop interaction regressions (#17970) |
|
Specific regression and serialization fi |
2026-08-24 |
| commit |
0.02 |
app: prevent Apps title bar overlap (#17925) |
|
Terse, issue-specific title with no AI-s |
2026-08-22 |
| commit |
0.02 |
launch: fall back to npx for DeepSeek Harness (#17758) |
|
Terse, conventional launch commit title |
2026-08-20 |
| commit |
0.02 |
polish onboarding layout and disable zoom (#17885) |
|
Terse, conventional commit title with sp |
2026-08-20 |
| commit |
0.02 |
app: add claude desktop app (#17899) |
|
Brief conventional commit title using pr |
2026-08-20 |
| commit |
0.02 |
app: add desktop onboarding flow (#17853) |
|
Terse conventional commit title describi |
2026-08-19 |
| commit |
0.02 |
Add a model metadata cache to reduce Ollama’s per-request ov |
|
Terse, conventional commit-style title w |
2026-08-18 |
| commit |
0.02 |
mlx update (#17761) |
|
Terse update title with no AI-style phra |
2026-08-15 |
| pr |
0.02 |
MLX: version bump |
|
Terse version-bump message with no AI-st |
2026-09-04 |
| pr |
0.02 |
server: propagate cloud stream failures |
|
Specific failure behavior and issue refe |
2026-09-09 |
| pr |
0.02 |
template: avoid mutating caller messages when collating |
|
Specific Go mutation analysis and measur |
2026-09-10 |
| pr |
0.02 |
model/parsers: fix gemma4 string placeholder collision with |
|
Highly specific failure mechanism, code |
2026-09-10 |
| pr |
0.02 |
server: allow parallel requests for qwen35 / qwen35moe now t |
|
Specific upstream issue history, archite |
2026-07-12 |
| pr |
0.02 |
README: add OpenHuman to Community Integrations |
|
Specific project details and concise wor |
2026-09-10 |
| pr |
0.02 |
model/parsers: avoid gemma4 string placeholder collisions |
|
Terse, specific parser details and valid |
2026-09-10 |
| pr |
0.02 |
fix(server): filter out namespace tools before sending to ll |
|
Specific implementation details and issu |
2026-08-08 |
| pr |
0.02 |
llm: key VRAM accounting on the child's actual log device na |
|
Contains highly specific device-placemen |
2026-09-09 |
| pr |
0.02 |
model/parsers: preserve large numeric tool arguments |
|
Precise numeric bug, parser names, and t |
2026-09-09 |
| pr |
0.02 |
model/parsers: avoid a panic when a tool call value is a lon |
|
Highly specific parser failure cases and |
2026-07-31 |
| pr |
0.02 |
docs: fix linux uninstall lib removal command |
|
Terse, specific commit-style explanation |
2026-09-09 |
| pr |
0.02 |
proxy: preserve stream failures and normalize namespaced com |
|
Terse, technical commit-style wording is |
2026-09-09 |
| pr |
0.02 |
ci: build desktop apps for app changes |
|
Concise technical description with speci |
2026-08-17 |
| pr |
0.02 |
api: expose projected context length in model details |
|
Brief, domain-specific wording lacks AI- |
2026-08-11 |
| pr |
0.02 |
api: use value receivers for tool String methods |
|
Highly domain-specific debugging explana |
2026-09-08 |
| pr |
0.02 |
fix(ui): ensure math symbols like $\rightarrow$ render corre |
|
Very terse informal description with a c |
2026-09-08 |
| pr |
0.02 |
docs: add CORS and HTTP 403 troubleshooting section |
|
Short, direct troubleshooting-section de |
2026-09-07 |
| commit |
0.01 |
llm: raise token repeat limit to 100 and return error instea |
|
Terse, domain-specific commit message wi |
2026-09-10 |
| commit |
0.01 |
openai: finalize responses at the web search limit (#18328) |
|
Terse, domain-specific commit title with |
2026-09-08 |
| commit |
0.01 |
app: add a first-use ChatGPT connection intro (#18321) |
|
Concise conventional commit title; no AI |
2026-09-08 |
| commit |
0.01 |
app: align ChatGPT connection status copy with Claude (#1832 |
|
Brief technical commit title with natura |
2026-09-08 |
| commit |
0.01 |
server/openai: retry compaction after context overflow (#183 |
|
Terse domain-specific title and conventi |
2026-09-08 |
| commit |
0.01 |
app: open Codex by default for Ollama launches (#18323) |
|
Concise technical commit title with repo |
2026-09-08 |
| commit |
0.01 |
fix data races in progress and sched (#18319) |
|
Specific concurrency details and technic |
2026-09-08 |
| commit |
0.01 |
app: preserve Codex configuration across host changes (#1824 |
|
Short conventional commit title without |
2026-09-08 |
| commit |
0.01 |
openai: use tsc_ prefix for tool search call IDs (#18296) |
|
Specific API terminology and concise com |
2026-09-08 |
| commit |
0.01 |
app: harden Codex desktop proxy handling (#18244) |
|
Terse, domain-specific commit title with |
2026-09-05 |
| commit |
0.01 |
openai: preserve images through response compaction (#18245) |
|
Terse, specific commit title; no signs o |
2026-09-05 |
| commit |
0.01 |
app: route Codex auto review through selected model (#18246) |
|
Concise technical commit title with natu |
2026-09-05 |
| commit |
0.01 |
ci: bound and cache the macOS MLX payload build (#18240) |
|
Concise, specific CI description with na |
2026-09-04 |
| commit |
0.01 |
app: add Ollama to ChatGPT Desktop (#18236) |
|
Terse, repository-specific commit-style |
2026-09-04 |
| commit |
0.01 |
openai: add Codex compaction support (#18224) |
|
Terse, domain-specific commit-style summ |
2026-09-04 |
| commit |
0.01 |
openai: add client tool search support (#18223) |
|
Terse, domain-specific commit-style summ |
2026-09-04 |
| commit |
0.01 |
ci: wire up MLX unit tests for PR runs (#17022) |
|
Technical CI notes include specific revi |
2026-09-01 |
| commit |
0.01 |
MLX, MLX-C: version bump (#18080) |
|
Brief version-bump message with informal |
2026-09-01 |
| commit |
0.01 |
build: go deps (#18161) |
|
Very terse dependency update with a conv |
2026-09-01 |
| commit |
0.01 |
proxy: continue requests when the model catalog changes (#18 |
|
Terse, issue-linked commit title with no |
2026-08-27 |
| commit |
0.01 |
app: restore system dark mode (#18049) |
|
Concise technical commit title; no free- |
2026-08-27 |
| commit |
0.01 |
app: consume Claude recommendation mappings (#18042) |
|
Specific, terse commit title with domain |
2026-08-26 |
| commit |
0.01 |
app: prevent Claude model picker scroll jumps (#18041) |
|
Concise issue-linked commit title with n |
2026-08-26 |
| commit |
0.01 |
linux: fix llama.cpp docker build (#18040) |
|
Brief, concrete build-fix explanation us |
2026-08-26 |
| commit |
0.01 |
docs: claude docs (#18006) |
|
Very terse documentation commit title. |
2026-08-26 |
| commit |
0.01 |
docs: document Claude Desktop integration (#18004) |
|
Concise, specific documentation commit t |
2026-08-26 |
| commit |
0.01 |
proxy: preserve string content during image fallback (#18002 |
|
Terse conventional commit with a specifi |
2026-08-25 |
| commit |
0.01 |
app: reset Claude Desktop models to defaults (#18000) |
|
Concise conventional commit message nami |
2026-08-25 |
| commit |
0.01 |
app: keep Claude toggle busy while connecting (#17997) |
|
Brief, domain-specific commit message wi |
2026-08-25 |
| commit |
0.01 |
app: reject browser origins on Claude Desktop gateway (#1798 |
|
Specific technical terminology and terse |
2026-08-25 |
| commit |
0.01 |
app: add Claude Desktop model mappings (#17979) |
|
Concise commit message describing a conc |
2026-08-25 |
| commit |
0.01 |
app: add Claude Desktop Auto mode setting (#17975) |
|
Short conventional commit naming a speci |
2026-08-25 |
| commit |
0.01 |
app: make integrations list scrollable (#17977) |
|
Terse, concrete UI change in standard co |
2026-08-25 |
| commit |
0.01 |
launch: disable claude code token countdown to preserve KV c |
|
Concise technical explanation with speci |
2026-08-22 |
| commit |
0.01 |
app: sign model recommendation endpoint (#17919) |
|
Short, conventional issue title. |
2026-08-22 |
| commit |
0.01 |
lint fixes (#17897) |
|
Minimal, informal commit message typical |
2026-08-20 |
| commit |
0.01 |
mlx update (#17886) |
|
Very terse project-specific maintenance |
2026-08-20 |
| commit |
0.01 |
llama.cpp update (#17851) |
|
Very terse update title; no evidence of |
2026-08-18 |
| pr |
0.01 |
docs: add ChatGPT Desktop integration |
|
Short conventional documentation title w |
2026-09-10 |
| pr |
0.01 |
mlxrunner: Evict prefix cache snapshots from the active conv |
|
Highly domain-specific explanation with |
2026-09-09 |
| pr |
0.01 |
server: handle thinking in native generate templates |
|
Terse, domain-specific fix description w |
2026-09-07 |
| pr |
0.01 |
model/parsers: parse Gemma 4 BEGIN_ARG tool calls |
|
Technical parser details and concrete va |
2026-09-07 |
| pr |
0.01 |
app: allow 1M context in settings |
|
Concise template content and test result |
2026-09-10 |
| pr |
0.01 |
model/parsers: preserve empty FunctionGemma arrays |
|
Brief, concrete parser change with focus |
2026-09-10 |
| pr |
0.01 |
fix(compat): honor tool_choice across OpenAI and Anthropic l |
|
Concise, issue-specific changelog with c |
2026-08-22 |
| pr |
0.01 |
app: fix ChatGPT model selector spacing |
|
Specific UI behavior and validation resu |
2026-09-09 |
| pr |
0.01 |
agent: name the searched directories when a skill is not fou |
|
Detailed code paths, callers, and observ |
2026-08-26 |
| pr |
0.01 |
docs: strip trailing whitespace in xcode guide |
|
Very brief, informal and specific mainte |
2026-09-09 |
| pr |
0.01 |
docs: fix bare faq link in gpu guide |
|
Terse, repository-specific link-fix expl |
2026-09-09 |
| pr |
0.01 |
docs: drop mdx extension on anthropic-compatibility link |
|
Concise commit message with a specific d |
2026-09-09 |
| pr |
0.01 |
docs: drop mdx extension on openai-compatibility link |
|
Concise commit message with a specific d |
2026-09-09 |
| pr |
0.01 |
openai: finalize responses at the web search limit |
|
Terse, specific commit-style wording wit |
2026-09-08 |
| pr |
0.01 |
app: align ChatGPT connection status copy with Claude |
|
Template-like structure contains concise |
2026-09-08 |
| pr |
0.01 |
server: retry compaction after context overflow |
|
Terse, concrete implementation summary w |
2026-09-08 |
| pr |
0.01 |
fix data races in progress and sched |
|
Terse, domain-specific commit message wi |
2026-09-08 |
| pr |
0.01 |
openai: use tsc_ prefix for tool search call IDs |
|
Terse, highly specific technical change |
2026-09-07 |
| pr |
0.01 |
docs: clarify ROCm visible device behavior |
|
Template-like validation summary with sp |
2026-04-29 |
| pr |
0.01 |
server: preserve parser tokens for raw generate |
|
Concise technical summary with precise i |
2026-06-30 |
| pr |
0.01 |
docs: sync launch integrations list with CLI |
|
Specific documentation mismatch with con |
2026-09-08 |
| pr |
0.01 |
docs: fix grammar in template guide |
|
Brief, targeted grammar correction with |
2026-09-08 |
| pr |
0.01 |
docs: fix resent typo in windows guide |
|
Contains a casual typo and specific docu |
2026-09-08 |
| pr |
0.01 |
docs: fix macOS casing in faq |
|
Concise casing correction tied to nearby |
2026-09-08 |
| pr |
0.01 |
types/model: increase maximum part length from 80 to 255 cha |
|
Terse, specific technical wording with i |
2026-09-08 |
| pr |
0.01 |
app: fix Go doc comments that name nonexistent methods |
|
Contains concrete file, symbol, and copy |
2026-09-07 |
| commit |
0.00 |
mlxrunner: wait for a killed runner to exit before the sched |
|
Highly specific concurrency and signal-h |
2026-09-09 |
| commit |
0.00 |
mlxrunner: bound MLX loads by system free memory while other |
|
Uses detailed Apple silicon and schedule |
2026-09-10 |
| commit |
0.00 |
mlxrunner: evict the active conversation's own checkpoints u |
|
Specific implementation behavior, model |
2026-09-09 |
| commit |
0.00 |
mlxrunner: keep the reused head of a cached edge safe from e |
|
Detailed cache and recurrent-layer behav |
2026-09-10 |
| commit |
0.00 |
mlxrunner: keep cache boundaries out of non-causal media ite |
|
Concise technical explanation with preci |
2026-09-09 |
| commit |
0.00 |
mlxrunner: capture whole-state at close for nodes split out |
|
References exact snapshot and eviction i |
2026-09-09 |
| commit |
0.00 |
llama.cpp: version bump b10864 (#18317) |
|
Minimal conventional version-bump commit |
2026-09-10 |
| commit |
0.00 |
app: fix ChatGPT model selector spacing (#18347) |
|
Terse, domain-specific commit message wi |
2026-09-09 |
| commit |
0.00 |
openai: support standalone named function outputs (#18348) |
|
Concise technical commit message, typica |
2026-09-09 |
| commit |
0.00 |
proxy: normalize namespaced commands in Full Access (#18331) |
|
Brief domain-specific commit message wit |
2026-09-09 |
| commit |
0.00 |
openai: accept plaintext-labeled Codex agent messages (#1832 |
|
Terse, technically precise commit messag |
2026-09-09 |
| commit |
0.00 |
mlxrunner: compile structured output as xgrammar structural |
|
Concise, domain-specific engineering pro |
2026-09-03 |
| commit |
0.00 |
mlxrunner: enable speculative decoding under structured outp |
|
Specific implementation details and ters |
2026-08-29 |
| commit |
0.00 |
gemma4: image and audio input support |
|
Specific MLX and Gemma4 implementation d |
2026-09-02 |
| commit |
0.00 |
mlxrunner: shared audio decoding and chunking for audio mode |
|
Detailed audio constraints and domain-sp |
2026-09-02 |
| commit |
0.00 |
mlxrunner: check every mlx-c call in the MLX bindings |
|
Terse commit style and precise binding d |
2026-09-02 |
| commit |
0.00 |
mlxrunner: capture MLX errors in a single buffer read after |
|
Specific error-handling changes and test |
2026-09-02 |
| commit |
0.00 |
mlx: fix mtp_test unit test (#18203) |
|
Terse conventional commit message with i |
2026-09-02 |
| commit |
0.00 |
llama.cpp: version bump b10760 (#18199) |
|
Standard concise version-bump commit mes |
2026-09-02 |
| commit |
0.00 |
mlx: dedup dependency files (#18159) |
|
— |
2026-09-01 |
| commit |
0.00 |
lint fix (#18081) |
|
— |
2026-08-28 |
| commit |
0.00 |
Clean up dead code (#17381) |
|
— |
2026-08-27 |
| commit |
0.00 |
app: list account cloud models for Claude (#18077) |
|
— |
2026-08-27 |
| commit |
0.00 |
app: synchronize macOS app handoff (#18056) |
|
— |
2026-08-27 |
| commit |
0.00 |
mlx: remove the text-only gemma3 model |
|
Detailed domain-specific explanation wit |
2026-08-25 |
| commit |
0.00 |
mlxrunner: avoid Metal GPU timeouts when loading models from |
|
Highly specific Metal, storage, and benc |
2026-08-25 |
| commit |
0.00 |
mlxrunner: add structured output support |
|
Domain-specific implementation and bench |
2026-08-14 |
| commit |
0.00 |
mlx: return exact types and evaluate arrays in the value rea |
|
Concise, implementation-specific explana |
2026-08-18 |
| commit |
0.00 |
llm: remove the unused Grammar completion-request field |
|
Terse, repository-specific cleanup descr |
2026-08-13 |
| commit |
0.00 |
llama.cpp: version bump b10630 (#18003) |
|
Minimal conventional version-bump messag |
2026-08-26 |
| commit |
0.00 |
MLX: version bump (#17955) |
|
Minimal conventional version-bump messag |
2026-08-26 |
| commit |
0.00 |
cmd: guard empty editor before indexing fields (#17067) |
|
Terse commit message with a standard sig |
2026-08-24 |
| commit |
0.00 |
mlxrunner: keep prefill snapshots when a request is cancelle |
|
Highly domain-specific explanation with |
2026-08-19 |
| commit |
0.00 |
mlxrunner: grow the prefix trie by whole child nodes so rest |
|
Detailed cache and trie terminology sugg |
2026-08-20 |
| commit |
0.00 |
mlxrunner: page out generated tokens when close records them |
|
Specific implementation and cache lifecy |
2026-08-20 |
| commit |
0.00 |
mlxrunner: clip prefill captures to their trie node's edge |
|
Concise technical explanation uses preci |
2026-08-20 |
| commit |
0.00 |
mlxrunner: settle the draft caches when a prefill is cancell |
|
Concrete failure mode and recurrent-laye |
2026-08-20 |
| commit |
0.00 |
qwen3.8: normalize system messages (#17855) |
|
Terse conventional commit-style descript |
2026-08-19 |
| commit |
0.00 |
ci: plumb temporary MLX patch through to docker stages (#178 |
|
Brief, repository-specific follow-up not |
2026-08-19 |
| commit |
0.00 |
mlx update (#17850) |
|
Extremely terse patch description with n |
2026-08-19 |
| pr |
0.00 |
llama.cpp: version bump b10864 |
|
Minimal version-bump message with no AI- |
2026-09-08 |
| pr |
0.00 |
Add Sefia-ai to Ollama Clients list |
|
Terse, informal wording strongly indicat |
2026-09-01 |
| pr |
0.00 |
docs: fix Large Language casing in macos and windows guides |
|
Very terse wording and minor casing shor |
2026-09-08 |
