1 Commits

Author SHA1 Message Date
b7d739bb6e chore(deps): update renovate/renovate docker tag to v43.76.5 2026-03-17 00:01:02 +00:00
5 changed files with 6 additions and 29 deletions

View File

@@ -15,8 +15,8 @@ spec:
spec:
containers:
- name: crawl4ai-proxy
image: gitea.lumpiasty.xyz/lumpiasty/crawl4ai-proxy-fit:latest
imagePullPolicy: Always
image: ghcr.io/lennyerik/crawl4ai-proxy:latest
imagePullPolicy: IfNotPresent
env:
- name: LISTEN_PORT
value: "8000"

View File

@@ -4,9 +4,7 @@ logToStdout: "both" # proxy and upstream
macros:
base_args: "--no-warmup --port ${PORT}"
common_args: "--fit-target 1024 --no-warmup --port ${PORT}"
gemma3_ctx_128k: "--ctx-size 131072"
qwen35_ctx_256k: "--ctx-size 262144"
common_args: "--fit-target 1536 --fit-ctx 65536 --no-warmup --port ${PORT}"
gemma_sampling: "--prio 2 --temp 1.0 --repeat-penalty 1.0 --min-p 0.00 --top-k 64 --top-p 0.95"
qwen35_sampling: "--temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 -ctk q4_0 -ctv q4_0"
qwen35_35b_args: "--temp 1.0 --min-p 0.00 --top-p 0.95 --top-k 20 -ctk q4_0 -ctv q4_0"
@@ -41,7 +39,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/gemma-3-12b-it-GGUF:Q4_K_M
${gemma3_ctx_128k}
${gemma_sampling}
${common_args}
@@ -49,7 +46,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/gemma-3-12b-it-GGUF:Q4_K_M
${gemma3_ctx_128k}
${gemma_sampling}
--no-mmproj
${common_args}
@@ -58,7 +54,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/gemma-3-4b-it-GGUF:Q4_K_M
${gemma3_ctx_128k}
${gemma_sampling}
${common_args}
@@ -66,7 +61,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/gemma-3-4b-it-GGUF:Q4_K_M
${gemma3_ctx_128k}
${gemma_sampling}
--no-mmproj
${common_args}
@@ -89,7 +83,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_35b_args}
${common_args}
@@ -97,7 +90,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_35b_args}
${common_args}
${thinking_off}
@@ -109,7 +101,6 @@ models:
/app/llama-server
-hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
${qwen35_35b_heretic_mmproj}
${qwen35_ctx_256k}
${qwen35_35b_args}
${common_args}
@@ -118,7 +109,6 @@ models:
/app/llama-server
-hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
${qwen35_35b_heretic_mmproj}
${qwen35_ctx_256k}
${qwen35_35b_args}
${common_args}
${thinking_off}
@@ -127,7 +117,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-0.8B-GGUF:Q4_K_XL
${qwen35_ctx_256k}
${qwen35_sampling}
${base_args}
${thinking_on}
@@ -145,7 +134,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_on}
@@ -154,7 +142,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_off}
@@ -163,7 +150,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_on}
@@ -172,7 +158,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_off}
@@ -182,7 +167,6 @@ models:
/app/llama-server
-hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
${qwen35_4b_heretic_mmproj}
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_on}
@@ -192,7 +176,6 @@ models:
/app/llama-server
-hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
${qwen35_4b_heretic_mmproj}
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_off}
@@ -201,7 +184,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_on}
@@ -210,7 +192,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_off}
@@ -219,7 +200,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-9B-GGUF:Q3_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_on}
@@ -228,7 +208,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-9B-GGUF:Q3_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_off}
@@ -237,7 +216,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-27B-GGUF:Q3_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_on}
@@ -246,7 +224,6 @@ models:
cmd: |
/app/llama-server
-hf unsloth/Qwen3.5-27B-GGUF:Q3_K_M
${qwen35_ctx_256k}
${qwen35_sampling}
${common_args}
${thinking_off}

View File

@@ -18,7 +18,7 @@ spec:
spec:
containers:
- name: llama-swap
image: ghcr.io/mostlygeek/llama-swap:v198-vulkan-b8369
image: ghcr.io/mostlygeek/llama-swap:v198-vulkan-b8352
imagePullPolicy: IfNotPresent
command:
- /app/llama-swap

View File

@@ -15,7 +15,7 @@ spec:
- name: renovate
# Update this to the latest available and then enable Renovate on
# the manifest
image: renovate/renovate:43.77.7-full
image: renovate/renovate:43.76.5-full
envFrom:
- secretRef:
name: renovate-gitea-token

View File

@@ -23,7 +23,7 @@ spec:
chart:
spec:
chart: openbao
version: 0.26.1
version: 0.26.0
sourceRef:
kind: HelmRepository
name: openbao