SyslogSolution/prose-contracts
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

no-mistakes(document): Fix stale compression-model docs across 4 contracts

Browse Source
This commit is contained in:
Abiba Bot
2026-07-19 00:31:54 +00:00
parent 3e246835d5
commit 6d975360d8
4 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gpu-fleet.prose.md
+7 -7
View File
@@ -125,7 +125,7 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
| Alias | RPM Cap | Routes To | Purpose | | Alias | RPM Cap | Routes To | Purpose |
|-------|---------|-----------|---------| |-------|---------|-----------|---------|
| `strix-moe` | 40 | Strix Halo | Compression tasks (MoE models) | | `strix-moe` | 40 | Strix Halo | Agent reasoning, compression (~30% via syslog-auto pool) (MoE models) |
| `gpu-dense` | 500 | RTX 3090 | Heavy reasoning | | `gpu-dense` | 500 | RTX 3090 | Heavy reasoning |
| `gpu-light` | 500 | RTX 5070 | Vision, web extract, light tasks | | `gpu-light` | 500 | RTX 5070 | Vision, web extract, light tasks |
@@ -136,7 +136,7 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
- syslog-auto → qwen → gemma → qwen3.6-35B-udq4 - syslog-auto → qwen → gemma → qwen3.6-35B-udq4
### Why Strix Halo RPM Is Capped ### Why Strix Halo RPM Is Capped
- Direct (strix-moe): 40 RPM (tight) — Strix Halo is shared with compression tasks - Direct (strix-moe): 40 RPM (tight) — Strix Halo handles agent reasoning + compression via syslog-auto pool
- Via syslog-auto: 60 RPM (moderate) — prevents flooding when multiple agents use syslog-auto simultaneously - Via syslog-auto: 60 RPM (moderate) — prevents flooding when multiple agents use syslog-auto simultaneously
- Combined max: ~100 RPM across both paths — Strix Halo can sustain this at 80°C - Combined max: ~100 RPM across both paths — Strix Halo can sustain this at 80°C
@@ -284,7 +284,7 @@ History stored at `/root/data/toks-history.json` with 7-day rolling window.
### Stable Aliases — CRITICAL ### Stable Aliases — CRITICAL
All agent configs MUST use stable role-based aliases, never model-specific names: All agent configs MUST use stable role-based aliases, never model-specific names:
- `compression.model: strix-moe` (NOT `qwen3.6-35B-udq4`) - `compression.model: syslog-auto` — switched from strix-moe 2026-07-18 to distribute across weighted pool (55% RTX 3090, 30% Strix Halo, 15% RTX 5070); relieves Strix Halo thermal pressure
- `auxiliary.vision.model: gpu-light` (NOT `gemma-4-12b`) - `auxiliary.vision.model: gpu-light` (NOT `gemma-4-12b`)
- `delegation.model: gpu-dense` (NOT `qwen3.6-27B-code`) - `delegation.model: gpu-dense` (NOT `qwen3.6-27B-code`)
- `auxiliary.web_extract.model: gpu-light` - `auxiliary.web_extract.model: gpu-light`
@@ -295,7 +295,7 @@ When the underlying model is swapped, only the LiteLLM config changes — agent
- RTX 3090: **128K** (reduced from 256K 2026-07-17) | RTX 5070: **128K** (reduced from 256K) | Strix Halo: **128K** - RTX 3090: **128K** (reduced from 256K 2026-07-17) | RTX 5070: **128K** (reduced from 256K) | Strix Halo: **128K**
- **All agents**: 128K ceiling — stable margin. For >128K workloads, use external providers (deepseek) - **All agents**: 128K ceiling — stable margin. For >128K workloads, use external providers (deepseek)
- Compression threshold 0.65: fires at ~85K (~43K headroom before 128K ceiling) - Compression threshold 0.65: fires at ~85K (~43K headroom before 128K ceiling)
- Mumuni compression model alias: `strix-moe` with 300s timeout - Mumuni compression model alias: `syslog-auto` (switched from strix-moe 2026-07-18) with 300s timeout
### Mumuni Agent Profile ### Mumuni Agent Profile
@@ -305,8 +305,8 @@ Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile i
|---------|-------|-------| |---------|-------|-------|
| `model.default` | `syslog-auto` | Weighted pool (55% qwen, 30% strix, 15% gemma) | | `model.default` | `syslog-auto` | Weighted pool (55% qwen, 30% strix, 15% gemma) |
| `model.provider` | `custom:litellm` | LiteLLM on CT116 | | `model.provider` | `custom:litellm` | LiteLLM on CT116 |
| `compression.model` | `strix-moe` | Stable alias — survives model swaps | | `compression.model` | `syslog-auto` | Switched from strix-moe 2026-07-18 — distributes across weighted pool |
| `aux.compression.model` | `strix-moe` | Compression auxiliary model | | `aux.compression.model` | `syslog-auto` | Compression auxiliary — switched from strix-moe 2026-07-18 |
| `aux.vision.model` | `gpu-light` | Vision tasks (RTX 5070) | | `aux.vision.model` | `gpu-light` | Vision tasks (RTX 5070) |
| `aux.web_extract.model` | `gpu-light` | Web extraction | | `aux.web_extract.model` | `gpu-light` | Web extraction |
| `delegation.model` | `gpu-dense` | Sub-agent reasoning (RTX 3090) | | `delegation.model` | `gpu-dense` | Sub-agent reasoning (RTX 3090) |
@@ -318,7 +318,7 @@ Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile i
| `personalities` | `creative` | Creative assistant personality | | `personalities` | `creative` | Creative assistant personality |
| Platforms | cli, discord, homeassistant, signal, telegram, zulip | All Hermes platforms | | Platforms | cli, discord, homeassistant, signal, telegram, zulip | All Hermes platforms |
| Main model timeout | 300s | LiteLLM global timeout | | Main model timeout | 300s | LiteLLM global timeout |
| Compression model timeout | 300s | strix-moe timeout increased from 120s | | Compression model timeout | 300s | syslog-auto timeout (switched from strix-moe 2026-07-18) |
### Agent Update Status (2026-07-15) ### Agent Update Status (2026-07-15)
gpu-self-heal.prose.md
+2 -2
View File
@@ -46,7 +46,7 @@ depends_on:
|-------|-----|------|-------|------|-----|-------|------| |-------|-----|------|-------|------|-----|-------|------|
| `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | ThinkingCap Qwen3.6-27B Q4_K_M + MTP + vision | 21.6/24.6GB (88%) | 128K | 74.9 | Heavy reasoning, code gen | | `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | ThinkingCap Qwen3.6-27B Q4_K_M + MTP + vision | 21.6/24.6GB (88%) | 128K | 74.9 | Heavy reasoning, code gen |
| `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | HauhauCS Gemma4-12B QAT Q4_K_M + MTP draft | 10.1/12.2GB (83%) | 128K | 169.6 | Vision, web extract, light tasks | | `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | HauhauCS Gemma4-12B QAT Q4_K_M + MTP draft | 10.1/12.2GB (83%) | 128K | 169.6 | Vision, web extract, light tasks |
| `strix-moe` | Strix Halo 64GB | ct15 (.15:8080) | Genesis Hermes V3 APEX (LuffyTheFox, 24GB) | ~10/64GB (16%) | 128K | 62.9 | Compression, summarization, long docs | | `strix-moe` | Strix Halo 64GB | ct15 (.15:8080) | Genesis Hermes V3 APEX (LuffyTheFox, 24GB) | ~10/64GB (16%) | 128K | 62.9 | Agent reasoning, compression (~30% via syslog-auto pool), summarization, long docs |
Key notes: Key notes:
- All models use direct GPU routing via LiteLLM (`api_key: not-needed`). Router (port 9000) is deprecated and NOT in the inference path. - All models use direct GPU routing via LiteLLM (`api_key: not-needed`). Router (port 9000) is deprecated and NOT in the inference path.
@@ -157,7 +157,7 @@ Key notes:
- **Target distribution**: - **Target distribution**:
- RTX 3090 (gpu-dense, 24GB, 74.9 tok/s) → Heavy reasoning, code gen, long conversations (slowest per-token but largest context capacity). Weight: 0.55 (LiteLLM). - RTX 3090 (gpu-dense, 24GB, 74.9 tok/s) → Heavy reasoning, code gen, long conversations (slowest per-token but largest context capacity). Weight: 0.55 (LiteLLM).
- RTX 5070 (gpu-light, 12GB, 169.6 tok/s) → Vision/image, web search, lightweight tasks (2.3x faster than 3090 per token). Weight: 0.15 (LiteLLM). - RTX 5070 (gpu-light, 12GB, 169.6 tok/s) → Vision/image, web search, lightweight tasks (2.3x faster than 3090 per token). Weight: 0.15 (LiteLLM).
- Strix Halo (strix-moe, 64GB, 62.9 tok/s) → Context compression, summarization, long docs (MoE model). Weight: 0.30 (LiteLLM). - Strix Halo (strix-moe, 64GB, 62.9 tok/s) → Agent reasoning, compression (~30% via syslog-auto pool), summarization, long docs (MoE model). Weight: 0.30 (LiteLLM).
- **Note**: RTX 5070 is the fastest endpoint per token. Route high-volume, low-complexity work there first. - **Note**: RTX 5070 is the fastest endpoint per token. Route high-volume, low-complexity work there first.
- **Fix**: - **Fix**:
- Alert if any GPU is handling workload outside its designated role - Alert if any GPU is handling workload outside its designated role
hermes-agent-baseline.prose.md
+1 -1
View File
@@ -5,7 +5,7 @@ version: 1.0.0
description: > description: >
Canonical known-good baseline for all Syslog Hermes agents. Captures the exact Canonical known-good baseline for all Syslog Hermes agents. Captures the exact
configuration state, keys, workarounds, and audit procedure. When an agent's configuration state, keys, workarounds, and audit procedure. When an agent's
configuration goes sideways, restore from this baseline. Last verified 2026-07-16. All GPUs 256K context (RTX 3090 .8, RTX 5070 .110, Strix Halo .15). Parallel 1 fleet-wide (Strix Halo handles compression solo). configuration goes sideways, restore from this baseline. Last verified 2026-07-16. All GPUs 128K context (RTX 3090 .8, RTX 5070 .110, Strix Halo .15). Parallel 1 fleet-wide (compression via syslog-auto pool — switched from strix-moe 2026-07-18).
author: Abiba (pi agent) author: Abiba (pi agent)
--- ---
inference-optimization.prose.md
+1 -1
View File
@@ -57,7 +57,7 @@ duration.
prefill time at 532 tok/s. Fix context first, routing second. prefill time at 532 tok/s. Fix context first, routing second.
- **Route by task**: ornith for multi-step reasoning only; qwen for code/standard - **Route by task**: ornith for multi-step reasoning only; qwen for code/standard
queries; gemma for compression/auxiliary. Never send simple completion to a queries; gemma for vision/web extraction; syslog-auto for compression (via weighted pool). Never send simple completion to a
35B MoE. 35B MoE.
- **Compress aggressively**: threshold at 40% (not 65%) — a 256K window should - **Compress aggressively**: threshold at 40% (not 65%) — a 256K window should
compact at 102K, not 166K. Target 15% tail (not 30%). compact at 102K, not 166K. Target 15% tail (not 30%).