Skip to content

Actions: apple/coreai-models

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
1,091 workflow runs
1,091 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Default prefill chunk to 4096 only at >=64GB memory CI #1075: Pull request #274 synchronize by stikves
13m 27s stikves:sukru/chunk-size-64gb-threshold
stikves:sukru/chunk-size-64gb-threshold
13m 27s
Exclude RMSNormGated from 4bit weight quantization (#277) (#281) CI #1074: Commit f7d42b1 pushed by stikves
10m 40s main
main
10m 40s
Default prefill chunk to 4096 only at >=64GB memory CI #1073: Pull request #274 synchronize by stikves
13m 22s stikves:sukru/chunk-size-64gb-threshold
stikves:sukru/chunk-size-64gb-threshold
13m 22s
Exclude RMSNormGated from 4bit weight quantization (#277) CI #1072: Pull request #281 synchronize by stikves
13m 22s stikves:sukru/fix-rmsnormgated-4bit-exclusion
stikves:sukru/fix-rmsnormgated-4bit-exclusion
13m 22s
Exclude RMSNormGated from 4bit weight quantization (#277) CI #1071: Pull request #281 synchronize by stikves
11m 0s stikves:sukru/fix-rmsnormgated-4bit-exclusion
stikves:sukru/fix-rmsnormgated-4bit-exclusion
11m 0s
Honor ContextOptions.reasoningLevel in the language model executor CI #1070: Pull request #267 synchronize by stikves
13m 36s stikves:sukru/fm-reasoning-level
stikves:sukru/fm-reasoning-level
13m 36s
Honor ContextOptions.reasoningLevel in the language model executor CI #1069: Pull request #267 synchronize by stikves
13m 40s stikves:sukru/fm-reasoning-level
stikves:sukru/fm-reasoning-level
13m 40s
Add reasoning_effort control to the LLM server (#263) CI #1068: Commit 0f0ce65 pushed by stikves
11m 5s main
main
11m 5s
Unify stop-token resolution across text and VLM adapters CI #1067: Pull request #269 synchronize by stikves
13m 53s stikves:sukru/vlm-additional-stop-tokens
stikves:sukru/vlm-additional-stop-tokens
13m 53s
Migrate Diffusion Quantization to Pre-Export CI #1066: Pull request #286 opened by kevchengcodes
10m 45s kevchengcodes:diffusion-quantization
kevchengcodes:diffusion-quantization
10m 45s
Add reasoning_effort control to the LLM server CI #1065: Pull request #263 synchronize by stikves
10m 47s stikves:sukru/reasoning-effort
stikves:sukru/reasoning-effort
10m 47s
Unify stop-token resolution across text and VLM adapters CI #1064: Pull request #269 synchronize by stikves
13m 38s stikves:sukru/vlm-additional-stop-tokens
stikves:sukru/vlm-additional-stop-tokens
13m 38s
Broaden tool-calling to Phi and Qwen3-Coder dialects CI #1063: Pull request #271 synchronize by stikves
10m 53s stikves:sukru/tool-call-dialects
stikves:sukru/tool-call-dialects
10m 53s
Default prefill chunk to 4096 only at >=64GB memory CI #1062: Pull request #274 synchronize by stikves
12m 54s stikves:sukru/chunk-size-64gb-threshold
stikves:sukru/chunk-size-64gb-threshold
12m 54s
Add --replay mode to the LLM server CI #1061: Pull request #266 synchronize by stikves
10m 53s stikves:sukru/server-replay-mode
stikves:sukru/server-replay-mode
10m 53s
Broaden tool-calling to Phi and Qwen3-Coder dialects CI #1060: Pull request #271 synchronize by stikves
10m 41s stikves:sukru/tool-call-dialects
stikves:sukru/tool-call-dialects
10m 41s
Add DFlash fused-target export pipeline (two-function drafter export + structural-metadata validation) CI #1059: Pull request #272 synchronize by stikves
10m 50s stikves:sukru/dflash-fused-export
stikves:sukru/dflash-fused-export
10m 50s
Add reasoning_effort control to the LLM server CI #1058: Pull request #263 synchronize by stikves
13m 31s stikves:sukru/reasoning-effort
stikves:sukru/reasoning-effort
13m 31s
CoreAISequentialEngine: idempotent generation via external session st… CI #1057: Commit c2ef849 pushed by stikves
10m 45s main
main
10m 45s
Broaden tool-calling to Phi and Qwen3-Coder dialects CI #1056: Pull request #271 synchronize by stikves
10m 50s stikves:sukru/tool-call-dialects
stikves:sukru/tool-call-dialects
10m 50s
CoreAISequentialEngine: idempotent generation via external session state CI #1055: Pull request #258 synchronize by stikves
10m 48s stikves:sukru/idempotent-engine
stikves:sukru/idempotent-engine
10m 48s
Add reasoning_effort control to the LLM server CI #1054: Pull request #263 synchronize by stikves
13m 37s stikves:sukru/reasoning-effort
stikves:sukru/reasoning-effort
13m 37s
Add DFlash fused-target export pipeline (two-function drafter export + structural-metadata validation) CI #1053: Pull request #272 synchronize by stikves
13m 19s stikves:sukru/dflash-fused-export
stikves:sukru/dflash-fused-export
13m 19s
Add --replay mode to the LLM server CI #1052: Pull request #266 synchronize by stikves
13m 42s stikves:sukru/server-replay-mode
stikves:sukru/server-replay-mode
13m 42s
Add backend-agnostic speculative decoding to llm-runner (Part 1) CI #1051: Pull request #284 synchronize by carinapeng
14m 15s carinapeng:carina/spec-decode-generic
carinapeng:carina/spec-decode-generic
14m 15s