| .. |
|
llama-quant-ffi
|
chore: Expand and optimize comprehensive test coverage (#1053)
|
2026-07-22 14:18:31 -04:00 |
|
llama-spec-bench
|
🚬 Add bounded MTP + N-gram pipelining for latency-limited split inference (#1026)
|
2026-07-22 18:32:34 +10:00 |
|
mesh-client
|
chore(code-quality): generalized code-quality refactoring (#1098)
|
2026-07-28 15:17:07 -04:00 |
|
mesh-llm
|
ci: compose reusable products and add Depot routing (#1113)
|
2026-07-30 04:02:53 -04:00 |
|
mesh-llm-api-client
|
chore: synchronize release version management (#934)
|
2026-06-30 22:42:09 -04:00 |
|
mesh-llm-api-server
|
chore: synchronize release version management (#934)
|
2026-06-30 22:42:09 -04:00 |
|
mesh-llm-build-info
|
feature(version): normalize version markers for different build types (#831)
|
2026-06-12 04:20:20 -04:00 |
|
mesh-llm-cli
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-commands
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-config
|
style(config): format logging schema
|
2026-08-01 03:21:09 -04:00 |
|
mesh-llm-console-server
|
feat: add plugin web UI extensions (#991)
|
2026-07-16 16:05:03 -04:00 |
|
mesh-llm-embedded-runtime
|
chore: improve embedded native-runtime compatibility guidance (#1043)
|
2026-07-26 19:22:26 -04:00 |
|
mesh-llm-events
|
feat(runtime): initialize local logging foundation
|
2026-07-31 16:52:23 -04:00 |
|
mesh-llm-ffi
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-gpu-bench
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-guardrails
|
Fix staged reasoning controls and MoA tool continuations (#1000)
|
2026-07-16 09:13:23 +10:00 |
|
mesh-llm-hardware-profile
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-host-runtime
|
feat(api): expose log queries and websocket replay
|
2026-08-01 03:31:43 -04:00 |
|
mesh-llm-identity
|
upgrade iroh to 1.0 (#894)
|
2026-06-22 10:37:46 +10:00 |
|
mesh-llm-log-store
|
feat(api): expose log queries and websocket replay
|
2026-08-01 03:31:43 -04:00 |
|
mesh-llm-native-runtime
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-node
|
fix: read-only model download caches (#1042)
|
2026-07-26 17:43:25 -04:00 |
|
mesh-llm-nodejs
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-plugin
|
chore: refactor Rust modules below 2,000 lines (#1019)
|
2026-07-19 09:09:48 -04:00 |
|
mesh-llm-plugin-manager
|
chore: harden management access and release integrity (#1007)
|
2026-07-17 07:17:14 -04:00 |
|
mesh-llm-protocol
|
feat(runtime): add daemon model lifecycle reconciliation (#1082)
|
2026-07-27 19:37:50 -04:00 |
|
mesh-llm-release-footer
|
fix: keep Windows release verifier native-ABI-free (#1114)
|
2026-07-29 16:06:23 -04:00 |
|
mesh-llm-routing
|
chore(code-quality): generalized code-quality refactoring (#1098)
|
2026-07-28 15:17:07 -04:00 |
|
mesh-llm-runtime-install
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-llm-sdk
|
chore: improve embedded native-runtime compatibility guidance (#1043)
|
2026-07-26 19:22:26 -04:00 |
|
mesh-llm-skills
|
feat: native rust SDK for rust consumers. (#736)
|
2026-06-03 12:39:19 +10:00 |
|
mesh-llm-system
|
fix: keep Windows release verifier native-ABI-free (#1114)
|
2026-07-29 16:06:23 -04:00 |
|
mesh-llm-test-harness
|
Upgrade workspace to Rust 2024 edition
|
2026-05-26 13:48:37 -04:00 |
|
mesh-llm-tui
|
chore: refactor Rust modules below 2,000 lines (#1019)
|
2026-07-19 09:09:48 -04:00 |
|
mesh-llm-types
|
chore(code-quality): generalized code-quality refactoring (#1098)
|
2026-07-28 15:17:07 -04:00 |
|
mesh-llm-ui
|
feat: unify release hosts and native runtimes
|
2026-07-29 10:16:23 -04:00 |
|
mesh-mixture-of-agents
|
Fix staged reasoning controls and MoA tool continuations (#1000)
|
2026-07-16 09:13:23 +10:00 |
|
metrics-server
|
add metrics server healthcheck (#871)
|
2026-06-18 15:56:24 +10:00 |
|
model-artifact
|
chore(code-quality): generalized code-quality refactoring (#1098)
|
2026-07-28 15:17:07 -04:00 |
|
model-hf
|
fix: use published mesh-llm-hf-hub crate (#1096)
|
2026-07-28 16:13:59 +10:00 |
|
model-package
|
fix: use published mesh-llm-hf-hub crate (#1096)
|
2026-07-28 16:13:59 +10:00 |
|
model-ref
|
fix(lint): many linter corrections (#696)
|
2026-05-26 18:00:06 -04:00 |
|
model-resolver
|
chore: synchronize release version management (#934)
|
2026-06-30 22:42:09 -04:00 |
|
openai-frontend
|
Pipeline MTP-anchored n-gram verify windows (#938)
|
2026-07-19 20:14:59 +10:00 |
|
skippy-bench
|
Refresh llama.cpp upstream patch queue (#1105)
|
2026-07-28 19:46:04 -04:00 |
|
skippy-cache
|
chore: synchronize release version management (#934)
|
2026-06-30 22:42:09 -04:00 |
|
skippy-coordinator
|
Lock split topology placement (#1050)
|
2026-07-22 14:04:25 +10:00 |
|
skippy-correctness
|
Refresh llama.cpp upstream patch queue (#1105)
|
2026-07-28 19:46:04 -04:00 |
|
skippy-ffi
|
Refresh llama.cpp upstream patch queue (#1105)
|
2026-07-28 19:46:04 -04:00 |
|
skippy-metrics
|
🚬 Add bounded MTP + N-gram pipelining for latency-limited split inference (#1026)
|
2026-07-22 18:32:34 +10:00 |
|
skippy-model-package
|
fix: read-only model download caches (#1042)
|
2026-07-26 17:43:25 -04:00 |
|
skippy-prompt
|
🚬 Add bounded MTP + N-gram pipelining for latency-limited split inference (#1026)
|
2026-07-22 18:32:34 +10:00 |
|
skippy-protocol
|
🚬 Add bounded MTP + N-gram pipelining for latency-limited split inference (#1026)
|
2026-07-22 18:32:34 +10:00 |
|
skippy-quantize
|
chore: Expand and optimize comprehensive test coverage (#1053)
|
2026-07-22 14:18:31 -04:00 |
|
skippy-runtime
|
Refresh llama.cpp upstream patch queue (#1105)
|
2026-07-28 19:46:04 -04:00 |
|
skippy-server
|
Refresh llama.cpp upstream patch queue (#1105)
|
2026-07-28 19:46:04 -04:00 |
|
skippy-topology
|
fix: resolve Qwen3.6 to the qwen35 recurrent family (#1109)
|
2026-07-30 04:06:09 +10:00 |
78384558e6