| COMMIT |
1.00 |
cmd/launch: add Copilot CLI integration (#15583) |
|
Commit message contains explicit AI assi |
2026-04-16 |
| COMMIT |
1.00 |
fix: improve error message for unknown input item type in re |
|
Commit message contains explicit AI assi |
2026-04-09 |
| PR |
1.00 |
mlx: update to 0.31.2 |
|
Explicitly states 'I used Codex to help' |
2026-04-24 |
| PR |
1.00 |
cmd: fix port typo in localhost test |
|
Explicit notice of autonomous AI assista |
2026-03-16 |
| PR |
1.00 |
api: allow localhost connections when auth signing fails |
|
Explicitly authored by an autonomous AI |
2026-03-16 |
| PR |
0.60 |
Add new model servam 30b and 105b |
|
Bot review and some awkward grammar; lik |
2026-03-08 |
| PR |
0.20 |
fix: print better error message when a new version of Ollama |
|
Somewhat formal but mostly template-driv |
2026-05-01 |
| PR |
0.20 |
fix: resolve OpenClaw gateway launch timeout on Windows by e |
|
Slightly formal template, root cause sec |
2026-04-21 |
| PR |
0.20 |
app: align the app launch page with ollama launch |
|
Detailed changelog but uses project and |
2026-04-22 |
| PR |
0.20 |
Improve error message for unsupported model architectures wi |
|
Slightly formal but direct, concise, and |
2026-04-28 |
| PR |
0.20 |
Add --private flag to ollama push |
|
Mostly template style; free text uses di |
2026-04-28 |
| PR |
0.19 |
feat(launch): add gemini target runner |
|
Some generic phrasing but still technica |
2026-04-27 |
| PR |
0.13 |
Harden Qwen-family tool payload rendering and fix Qwen 3.5 t |
|
Detailed technical summary; contains hum |
2026-04-23 |
| COMMIT |
0.10 |
create: avoid gc race with create (#15628) |
|
Technical commit message with informal t |
2026-04-16 |
| COMMIT |
0.10 |
gemma4: render differently based on model size |
|
Uses domain jargon and an informal chang |
2026-04-15 |
| COMMIT |
0.10 |
gemma4: restore e2b-style nothink prompt (#15560) |
|
Technical, concise, uses domain-specific |
2026-04-13 |
| COMMIT |
0.10 |
mac: prevent generate on cross-compiles (#15120) |
|
Concise, informal reasoning with domain- |
2026-04-13 |
| COMMIT |
0.10 |
mlx: add op wrappers for Conv2d, Pad, activations, trig, and |
|
Domain jargon, commit-style writing, not |
2026-04-13 |
| COMMIT |
0.10 |
mlx: mixed-precision quant and capability detection improvem |
|
Technical changelog, uses domain languag |
2026-04-13 |
| COMMIT |
0.10 |
gemma4: fix compiler error on metal (#15550) |
|
Technical and concise, clear bugfix moti |
2026-04-13 |
| COMMIT |
0.10 |
gemma4: update renderer to match new jinja template (#15490) |
|
Informal tone, domain content, brief lis |
2026-04-10 |
| COMMIT |
0.10 |
docs: add hermes agent integration guide (#15488) |
|
Mostly changelog and technical, no AI si |
2026-04-10 |
| COMMIT |
0.10 |
model/parsers: suppress extra gemma4 closing tool tags (#153 |
|
Technical description with informal phra |
2026-04-06 |
| PR |
0.10 |
create: keep linear_attn in_proj_qkv and in_proj_z in BF16 f |
|
Technical summary with tables, some temp |
2026-04-30 |
| PR |
0.10 |
Fix qwen35/qwen35moe architecture aliases in llama.cpp parse |
|
Includes error output and technical deta |
2026-04-27 |
| PR |
0.10 |
fix: respect format parameter when think is disabled for qwe |
|
Template-based, technical, with domain a |
2026-03-18 |
| PR |
0.10 |
server: apply format constraint when thinking is disabled |
|
Technical, domain-focused, template stru |
2026-03-06 |
| PR |
0.10 |
mlxrunner: add decode checkpoints for exact-restore caches |
|
Narrative with personal reasoning, infor |
2026-05-01 |
| PR |
0.10 |
Docs/add ClearFrame agent governance framework to integratio |
|
Contains domain-specific jargon and link |
2026-05-01 |
| PR |
0.10 |
llama: add qwen35/qwen35moe architecture support for communi |
|
Detailed technical content, natural expe |
2026-04-30 |
| PR |
0.10 |
cuda: prevent Gemma 4 Dense FA hang for head_dim=512 |
|
Technical details, concise changelog, no |
2026-04-30 |
| PR |
0.10 |
x/imagegen: restore image editing dispatch for flux2 models |
|
Structured technical explanation with do |
2026-02-25 |
| PR |
0.10 |
renderers: update gemma4 renderer |
|
Informal style and technical commentary, |
2026-04-30 |
| PR |
0.10 |
server: verify blob downloads with an inline sha256 hasher |
|
Detailed but uses informal language and |
2026-04-10 |
| PR |
0.10 |
fix: preserve partial chunk progress before returning fatal |
|
Uses technical terms and notes; informal |
2026-03-23 |
| PR |
0.10 |
server: cancel pull on client disconnect |
|
Project-specific language and informal n |
2026-04-29 |
| PR |
0.10 |
docs: clarify Modelfile file format |
|
Structured template, brief free-text; hu |
2026-04-28 |
| PR |
0.10 |
ggml-metal: fix mixed bf16/f16 cooperative tensor operand or |
|
Technical details and direct language po |
2026-04-14 |
| PR |
0.10 |
runner/ollamarunner: handle sampling errors gracefully |
|
Uses technical jargon and an informal, c |
2026-03-17 |
| PR |
0.10 |
scripts: wait for graphical.target in systemd service |
|
Natural, concise language with technical |
2026-03-17 |
| PR |
0.10 |
server: preserve chat metrics across buffered tool chunks |
|
Bullet points and test commands; technic |
2026-04-28 |
| PR |
0.10 |
x/mlxrunner: apply config.json per-tensor quant overrides fo |
|
Explains PR lineage and technical fixes |
2026-04-23 |
| PR |
0.10 |
cmd/launch: add OpenClaude integration |
|
Domain-specific detail and informal tech |
2026-04-16 |
| PR |
0.10 |
server: preserve generate logprobs with builtin parsers |
|
Domain-specific terms and brief issue co |
2026-04-26 |
| PR |
0.10 |
docs(modelfile): document creating vision models |
|
Personal anecdote, casual tone, domain r |
2025-06-22 |
| PR |
0.10 |
Add metrics endpoint and basic request metrics otel based |
|
Casual phrasing, test instructions, doma |
2024-08-27 |
| PR |
0.10 |
create: prune imported blobs and startup invalid leftovers |
|
Contains domain jargon and concise expla |
2026-04-25 |
| PR |
0.09 |
Add `ollama launch qwen` support for Qwen Code CLI |
|
Domain-specific phrasing, concise change |
2026-04-25 |
| PR |
0.09 |
readme: add spell to Terminal & CLI community integrations |
|
Domain-specific language, not overly for |
2026-04-30 |
| PR |
0.09 |
Model support for batching |
|
Technical detail, informal, domain-speci |
2026-04-25 |
| PR |
0.09 |
ggml: check for overflow when computing tensor byte strides |
|
Technical, domain-specific bugfix explan |
2026-04-27 |
| PR |
0.08 |
launch: add codex model metadata catalog |
|
Domain jargon, minimal formal phrasing, |
2026-04-24 |
| PR |
0.08 |
docs: fix linux tar.zst extraction |
|
Human summary, duplicate check, testing |
2026-04-30 |
| PR |
0.08 |
Add missing hipBLASLt kernels and some gfx targets cleanup |
|
ROCm, hipBLASLt, Windows specifics, tech |
2026-03-20 |
| PR |
0.08 |
app/server: fix desktop app startup killing active `ollama l |
|
Informal phrasing and domain details; hu |
2026-04-17 |
| PR |
0.08 |
app/ui: fix sidebar animating open on initial load |
|
Informal problem explanation and technic |
2026-04-22 |
| PR |
0.08 |
launch: add codex model metadata catalog |
|
Domain jargon, minimal formal phrasing, |
2026-04-23 |
| PR |
0.07 |
server: apply format constraint for all thinking parsers whe |
|
Uses domain terms, table-driven test men |
2026-04-30 |
| PR |
0.07 |
cmd: add regression test for escaped iCloud image paths |
|
Human justification and validation steps |
2026-04-28 |
| PR |
0.06 |
docs: add HuggingFace Hub direct GGUF pull pattern to import |
|
Casual domain-focused language, specific |
2026-04-23 |
| COMMIT |
0.05 |
New models (#15861) |
|
Terse, technical changelog content; doma |
2026-04-28 |
| COMMIT |
0.05 |
mlx: Support NVIDIA TensorRT Model Optimizer import (#15566) |
|
Detailed, technical content with domain |
2026-04-28 |
| COMMIT |
0.05 |
tokenizer: fix multi-regex BPE offset handling (#15844) |
|
Commit message is terse and technical wi |
2026-04-27 |
| COMMIT |
0.05 |
docs: update structured outputs doc for cloud (#15733) |
|
Concise doc update; domain-specific and |
2026-04-22 |
| PR |
0.05 |
docs: add Spanish (es) README translation |
|
Concise, technical, uses domain terms; n |
2026-03-04 |
| PR |
0.05 |
Add model eval metrics to /metrics |
|
Technical, terse changelog; domain-speci |
2025-06-22 |
| PR |
0.05 |
fix: add URL validation in openai.go |
|
Uses template; summary/description have |
2026-04-29 |
| PR |
0.05 |
fix(mlxrunner): preserve fp32 precision in gated_delta_step |
|
Technical, uses domain jargon, fragment |
2026-04-29 |
| PR |
0.05 |
server/launch: add model recommendations cache endpoint |
|
Template-driven, experimental notes; dom |
2026-04-28 |
| PR |
0.05 |
launch: fetch recommended models from server endpoint |
|
Technical, concise summary; domain detai |
2026-04-14 |
| PR |
0.05 |
mlx: qwen3.5 vision support |
|
Technical, informal, includes review con |
2026-03-19 |
| PR |
0.05 |
mlx: Support NVIDIA TensorRT Model Optimizer import |
|
Brief, informal follow-up; human approva |
2026-04-14 |
| PR |
0.05 |
docs(context-length): add Linux (systemd) section for OLLAMA |
|
Domain-specific Linux/systemd context, n |
2026-04-28 |
| PR |
0.05 |
tokenizer: fix multi-regex BPE offset handling |
|
Technical commit message, domain-specifi |
2026-04-27 |
| PR |
0.05 |
fix: improve error handling for model loading in Scheduler |
|
Terse technical language, clear fix desc |
2026-04-25 |
| PR |
0.05 |
Add Atlarix to Code Editors & Development integrations |
|
Contains domain jargon and technical det |
2026-04-24 |
| PR |
0.05 |
openai: map responses reasoning effort to think |
|
Structured technical changelog, domain-s |
2026-04-24 |
| COMMIT |
0.00 |
app: source featured models from experimental recommendation |
|
Terse, domain-specific changelog; no AI |
2026-05-01 |
| COMMIT |
0.00 |
fix: resolve OpenClaw gateway launch timeout on Windows by e |
|
Short, technical fix message; informal a |
2026-05-01 |
| COMMIT |
0.00 |
metal: harden for ggml initialization failures (#15755) |
|
Technical detail and iterative edits; hu |
2026-04-30 |
| COMMIT |
0.00 |
app: remove ollama update url env var used for testing (#159 |
|
Terse commit message with domain context |
2026-04-30 |
| COMMIT |
0.00 |
renderers: update gemma4 renderer (#15886) |
|
Short, technical message; human style. |
2026-04-30 |
| COMMIT |
0.00 |
launch: use vram bytes for model recommendations (#15885) |
|
Concise, domain-specific commit message; |
2026-04-30 |
| COMMIT |
0.00 |
launch/docs: fix title for pool (#15883) |
|
Concise commit message; style is human-l |
2026-04-29 |
| COMMIT |
0.00 |
app: align the app launch page with ollama launch (#15753) |
|
Brief and to the point commit message wi |
2026-04-29 |
| COMMIT |
0.00 |
server/launch: add model recommendations cache endpoint (#15 |
|
Technical commit message using project t |
2026-04-29 |
| COMMIT |
0.00 |
mlxrunner: decouple models from attention cache storage layo |
|
Technical language, abbreviations, infor |
2026-04-22 |
| COMMIT |
0.00 |
mlxrunner: apply RoPE at per-row positions |
|
Technical explanation and casual phrasin |
2026-04-21 |
| COMMIT |
0.00 |
mlxrunner: wrap model forward inputs in a Batch struct |
|
Concise, technical, informal changelog; |
2026-04-21 |
| COMMIT |
0.00 |
app/server: fix desktop app startup killing active `ollama l |
|
Brief bugfix summary; no evidence of AI- |
2026-04-28 |
| COMMIT |
0.00 |
mlxrunner: batch the sampler across multiple sequences |
|
Concise technical wording, domain-specif |
2026-04-21 |
| COMMIT |
0.00 |
mlxrunner: track sampler history in a fixed-size ring buffer |
|
Terse commit, domain-specific technical |
2026-04-20 |
| COMMIT |
0.00 |
openai: map responses reasoning effort to think (#15789) |
|
Terse, domain-specific commit message; n |
2026-04-24 |
| COMMIT |
0.00 |
api: accept "max" as a think value (#15787) |
|
Short, technical summary; standard human |
2026-04-24 |
| COMMIT |
0.00 |
launch: harden OpenClaw onboarding flow (#15777) |
|
Succinct commit message with domain-spec |
2026-04-23 |
| COMMIT |
0.00 |
launch: resave managed integration config when live config d |
|
Concise, technical language; typical hum |
2026-04-23 |
| COMMIT |
0.00 |
launch: keep launch recommended models in a fixed canonical |
|
Terse commit message with domain-specifi |
2026-04-23 |
| COMMIT |
0.00 |
launch: use bundled OpenClaw ollama web search (#15757) |
|
Short, technical commit; informal wordin |
2026-04-22 |
| COMMIT |
0.00 |
launch: replace kimi-k2.5 with k2.6 as top recommended model |
|
Short, technical commit summary; human s |
2026-04-21 |
| COMMIT |
0.00 |
mlxrunner: tokenize prompts in request handler goroutines |
|
Detailed technical writing with domain j |
2026-04-03 |
| COMMIT |
0.00 |
mlx: improve thread safety of array management |
|
Technical, detailed and with inline rema |
2026-04-03 |
| COMMIT |
0.00 |
app/ui: fix model picker showing stale model after switching |
|
Includes bug details and terse explanati |
2026-04-21 |
| COMMIT |
0.00 |
cmd: populate model capabilities in launchInteractiveModel ( |
|
References prior PR and bug, highly spec |
2026-04-21 |
| COMMIT |
0.00 |
mlxrunner: fuse top-P and top-K into a single sort pass |
|
Technical improvement with domain vocabu |
2026-04-16 |
| COMMIT |
0.00 |
mlxrunner: use MaxAxis in the min-P sampler |
|
Very terse, technical, domain-specific; |
2026-04-16 |
| COMMIT |
0.00 |
mlxrunner: add logprobs support |
|
Concise, domain-specific; matches human |
2026-04-16 |
| COMMIT |
0.00 |
server: apply format when think=false for gemma4 (#15678) |
|
One-line ticket close, matches accepted |
2026-04-21 |
| COMMIT |
0.00 |
launch: add kimi cli integration with installer flow (#15723 |
|
Concise commit message; no AI hallmarks. |
2026-04-20 |
| COMMIT |
0.00 |
mlx: fuse sigmoid router head in glm4_moe_lite |
|
Technical, domain-specific; human-writte |
2026-04-15 |
| COMMIT |
0.00 |
mlx: apply repeat penalties in sampler (#15631) |
|
Very terse commit message, classic human |
2026-04-18 |
| COMMIT |
0.00 |
docs: update hermes (#15655) |
|
Standard doc update commit; no AI signal |
2026-04-17 |
| COMMIT |
0.00 |
cmd/launch: show WSL guidance on Windows instead of handing |
|
Terse, domain-specific commit; no AI mar |
2026-04-17 |
| COMMIT |
0.00 |
launch: skip unchanged managed-single rewrite (#15633) |
|
Concise, technical language with no AI c |
2026-04-16 |
| COMMIT |
0.00 |
mlx: additional gemma4 cache fixes (#15607) |
|
Brevity, domain-specific, informal; no A |
2026-04-16 |
| COMMIT |
0.00 |
mlx: fix gemma4 cache to use logical view (#15617) |
|
Short, terse, and domain-specific; no AI |
2026-04-16 |
| COMMIT |
0.00 |
mlx: fix imagegen lookup (#15588) |
|
Domain-specific, includes references/typ |
2026-04-16 |
| COMMIT |
0.00 |
make empty block conditional |
|
Extremely brief and direct; no sign of A |
2026-04-15 |
| COMMIT |
0.00 |
Keep Gemma4 router projection in source precision (#15613) |
|
Short technical title, no AI hallmarks o |
2026-04-15 |
| COMMIT |
0.00 |
launch: always list cloud recommendations first (#15593) |
|
Concise, informal, clearly human-written |
2026-04-15 |
| COMMIT |
0.00 |
launch: add hermes (#15569) |
|
Brief technical commit, no signs of AI p |
2026-04-15 |
| COMMIT |
0.00 |
mlx: fix RotatingKVCache.concat() dropping context on mid-ro |
|
Detailed technical commit, domain jargon |
2026-04-15 |
| COMMIT |
0.00 |
mlx: Improve gemma4 performance with fused operations (#1558 |
|
Changelog format, domain-specific, no AI |
2026-04-15 |
| COMMIT |
0.00 |
models: fuse MLP activation functions via mlx_compile |
|
Technical description, domain-specific, |
2026-04-13 |
| COMMIT |
0.00 |
mlx: add compiled closure support |
|
Technical and concise, structure is typi |
2026-04-13 |
| COMMIT |
0.00 |
launch: OpenCode inline config (#15586) |
|
Concise commit message with standard hum |
2026-04-14 |
| COMMIT |
0.00 |
launch/openclaw: fix --yes flag behaviour to skip channels c |
|
Standard technical fix description, ters |
2026-04-14 |
| COMMIT |
0.00 |
Revert "launch/opencode: use inline config (#15462)" (#15568 |
|
Typical revert message from GitHub, no A |
2026-04-14 |
| COMMIT |
0.00 |
launch: skip unchanged integration rewrite configration (#15 |
|
Brief summary with a typo, likely human- |
2026-04-14 |
| COMMIT |
0.00 |
Gemma4 on MLX (#15244) |
|
Technical changelog with informal and do |
2026-04-13 |
| COMMIT |
0.00 |
launch/opencode: use inline config (#15462) |
|
Pure changelog, no free-text aside from |
2026-04-13 |
| COMMIT |
0.00 |
Revert "gemma4: fix nothink case renderer (#15553)" (#15556) |
|
Standard revert message, no free-text ev |
2026-04-13 |
| COMMIT |
0.00 |
cgo: suppress deprecated warning to quiet down go build (#15 |
|
Changelog style, no evidence of AI-gener |
2026-04-13 |
| COMMIT |
0.00 |
Revert "gemma4: add nothink renderer tests (#15554)" (#15555 |
|
Template revert, no free-text for AI ana |
2026-04-13 |
| COMMIT |
0.00 |
gemma4: add nothink renderer tests (#15554) |
|
Brief and project-specific explanation, |
2026-04-13 |
| COMMIT |
0.00 |
gemma4: fix nothink case renderer (#15553) |
|
Terse, domain-specific commit message wi |
2026-04-13 |
| COMMIT |
0.00 |
Update to ROCm 7.2.1 (#15483) |
|
Commit uses a human co-author GitHub tra |
2026-04-12 |
| COMMIT |
0.00 |
gemma4: be less strict about whitespace before bare keys (#1 |
|
Terse, informal style; clear domain cont |
2026-04-11 |
| COMMIT |
0.00 |
model/parsers: fix missing parallel tool call indices (#1546 |
|
Direct changelog style, terse; clearly h |
2026-04-10 |
| COMMIT |
0.00 |
app/ui: re-validate image attachments when selected model ch |
|
No free-text, only title; human or templ |
2026-04-10 |
| COMMIT |
0.00 |
launch: update openclaw channel message (#15463) |
|
Very terse commit message, no stylistic |
2026-04-09 |
| COMMIT |
0.00 |
launch: add re-run hint to dependency error message (#15439) |
|
Terse, domain-specific and informal phra |
2026-04-09 |
| COMMIT |
0.00 |
modelfiles: fix /save command and add shortname for safetens |
|
Contains domain detail, numbered issues; |
2026-04-09 |
| COMMIT |
0.00 |
mlx: remove stale x86 libmlx library (#15443) |
|
Short, informal; clear reference to prio |
2026-04-09 |
| COMMIT |
0.00 |
app: restore launch default and refine launch sidebar open f |
|
Brief, technical, and lacks AI-typical s |
2026-04-08 |
| COMMIT |
0.00 |
pull/push: refine safetensors (#14946) |
|
Domain-specific details, informal change |
2026-04-08 |
| COMMIT |
0.00 |
launch/opencode: detect `curl` installed opencode at `~/.ope |
|
No free-text, terse and technical commit |
2026-04-08 |
| COMMIT |
0.00 |
launch: add openclaw channels setup (#15407) |
|
No free-text, direct technical summary. |
2026-04-08 |
| COMMIT |
0.00 |
launch: update ctx length for glm-5.1 and gemma4 (#15411) |
|
Brief, technical, with human-style conte |
2026-04-08 |
| COMMIT |
0.00 |
cmd: improve multi-select sorting and selection status (#152 |
|
Short, informal summary, no AI-like phra |
2026-04-08 |
| COMMIT |
0.00 |
responses: add support for fn call output arrays (#15406) |
|
Technical with error logs, informal and |
2026-04-07 |
| COMMIT |
0.00 |
app/ui: fix lint errors for unused vars, prefer-const, and e |
|
Changelog style, terse and technical. |
2026-04-07 |
| COMMIT |
0.00 |
gemma4: Disable FA on older GPUs where it doesn't work (#154 |
|
Brief, technical commit with domain cont |
2026-04-07 |
| COMMIT |
0.00 |
mlx: use default http client (#15405) |
|
No free-text commentary, only standard s |
2026-04-07 |
| COMMIT |
0.00 |
gemma4: add missing file (#15394) |
|
Succinct explanation, normal for human c |
2026-04-07 |
| COMMIT |
0.00 |
create: Clean up experimental paths, fix create from existi |
|
Structured changelog with terse explanat |
2026-04-07 |
| COMMIT |
0.00 |
gemma4: enable flash attention (#15378) |
|
Technical terminology and direct phrasin |
2026-04-07 |
| COMMIT |
0.00 |
mlx: Improve M5 performance with NAX (#15345) |
|
Expansive technical commit, uses domain- |
2026-04-07 |
| COMMIT |
0.00 |
model/parsers: add gemma4 tool call repair (#15374) |
|
Technical explanation with domain detail |
2026-04-07 |
| COMMIT |
0.00 |
launch/openclaw: patch approvedScopes baseline for TUI pairi |
|
No free-text, just a standard, short com |
2026-04-07 |
| COMMIT |
0.00 |
app: update featured models (#15373) |
|
Concise task description, typical of hum |
2026-04-06 |
| COMMIT |
0.00 |
app: default app home view to new chat instead of launch (#1 |
|
Terse commit message, informal and speci |
2026-04-04 |
| PR |
0.00 |
Add libquadmath0 to Dockerfile dependencies |
|
Brief justification; natural for human c |
2026-05-01 |
| PR |
0.00 |
runner: Remove CGO engines, use llama-server exclusively for |
|
Long, but contains WIP, domain shorthand |
2026-03-28 |
| PR |
0.00 |
mlx: follow up for gemma4 |
|
Very brief followup with issue reference |
2026-04-13 |
| PR |
0.00 |
MLX: add repeatable model porting workflow |
|
Informal, roadmap notes, and abrupt cuto |
2026-04-13 |
| PR |
0.00 |
convert: support fp8 safetensors import |
|
Technical jargon, concise explanation, a |
2026-04-20 |
| PR |
0.00 |
launch/opencode: add image modalities for vision models |
|
Template summary plus custom technical d |
2026-05-01 |
| PR |
0.00 |
app: source featured models from experimental recommendation |
|
Clear technical change summary using dom |
2026-04-30 |
| PR |
0.00 |
cmd/launch: add Qwen code integration |
|
Uses domain details and informal tone; l |
2026-04-30 |
| PR |
0.00 |
launch: repair missing editor config before launch |
|
Structured changelog, with technical det |
2026-05-01 |
| PR |
0.00 |
Update MLX and MLX-C with threading fixes |
|
Concise technical commit message, no AI |
2026-04-27 |
| PR |
0.00 |
test: integration test hardening |
|
Terse informal commit message, definitel |
2025-12-19 |
| PR |
0.00 |
ci: speed up release builds |
|
Informal summary and changelog; no AI ma |
2026-03-25 |
| PR |
0.00 |
metal: harden for ggml initialization failures |
|
Technical, informal, uses test details a |
2026-04-22 |
| PR |
0.00 |
Add local bundle check before downloading ollama |
|
Specific, context-rich explanation, tech |
2026-01-08 |
| PR |
0.00 |
go: bump to 1.26 |
|
Specific changelog and test plan; reads |
2026-04-30 |
| PR |
0.00 |
app: remove ollama update url env var used for testing |
|
Casual justification, brief and natural; |
2026-04-30 |
| PR |
0.00 |
cmd/launch: improve integration backup UX |
|
Changelog with technical examples, no AI |
2026-04-30 |
| PR |
0.00 |
added LexiChat desktop app link |
|
Short, informal, and terse commit descri |
2026-04-30 |
| PR |
0.00 |
launch: use vram bytes for model recommendations |
|
Short, informal summary, no AI phrasing. |
2026-04-30 |
| PR |
0.00 |
launch/docs: fix title for pool |
|
Extremely terse commit message with no A |
2026-04-29 |
| PR |
0.00 |
docs: clarify ROCm visible device behavior |
|
Clear human style with domain jargon and |
2026-04-29 |
| PR |
0.00 |
Improve https://github.com/ollama/ollama/pull/14864 (Update |
|
Contains typos, casual tone, and technic |
2026-03-28 |
| PR |
0.00 |
Intel level zero |
|
Extremely terse, lacks AI hallmarks. |
2026-04-29 |
| PR |
0.00 |
fix(cmd): correct port typo in TestIsLocalhost |
|
Brief, factual changelog with no excess |
2026-03-17 |
| PR |
0.00 |
New models |
|
Title only; no content to assess for AI |
2026-04-28 |
| PR |
0.00 |
Improve error message for unsupported model architectures |
|
Human tone with domain-specific rational |
2026-04-27 |
| PR |
0.00 |
README: add Xpdite to community integrations |
|
Brief, informal description; typical hum |
2026-04-27 |
| PR |
0.00 |
Add riscv64 support |
|
Detailed, technical, with platform refer |
2026-04-27 |
| PR |
0.00 |
app: restore macOS runtime env for managed server |
|
Technical content, informal truncation, |
2026-04-13 |
| PR |
0.00 |
ml: skip init validation for MIG GPU devices |
|
Domain-specific debugging steps and ters |
2026-01-23 |
| PR |
0.00 |
Add /api/tokenize and /api/detokenize endpoints for model-al |
|
Technical summary with bullet lists and |
2025-08-22 |
| PR |
0.00 |
app.py erstellen |
|
No free-text description, German languag |
2026-03-03 |
| PR |
0.00 |
fix: improve image path regex for special characters |
|
Commit message is domain-specific, no AI |
2026-04-26 |
| PR |
0.00 |
mlxrunner: batch the sampler across multiple sequences |
|
Concise technical wording, matches human |
2026-04-21 |
| PR |
0.00 |
runner: expose prompt cache hit count in completion response |
|
Detailed technical explanation, natural |
2026-04-23 |
| PR |
0.00 |
Use LXCFS' formula to compute free memory in a cgroup |
|
Informal, confident tone, domain referen |
2026-01-19 |
| PR |
0.00 |
docs: add RDNA4 / gfx1201 ROCm build instructions to develop |
|
Technical doc update, domain-specific te |
2026-04-25 |
| PR |
0.00 |
Add token usage for cloud model streaming (inject stream_opt |
|
Technical summary, domain details, natur |
2026-04-02 |
| PR |
0.00 |
kvcache: add TurboQuant compressed KV cache (tq2/tq3/tq2k/tq |
|
Technical with abbreviations and table; |
2026-04-11 |
