143 Commits

Author	SHA1	Message	Date
Lumpiasty	6096b7019d	fix path to llama-server binary	2026-05-23 09:32:11 +02:00
Renovate	37d42a8dd8	Update ghcr.io/mostlygeek/llama-swap Docker tag to unified-vulkan-2026-05-23	2026-05-23 07:25:07 +00:00
Lumpiasty	c161da3657	add mlock and disable mmap in llama-server	2026-05-21 23:18:05 +02:00
Lumpiasty	fc2c15d154	move whisper to gpu	2026-05-21 22:02:34 +02:00
Lumpiasty	02b3ec13b4	switch kokoro to remsky/Kokoro-FastAPI	2026-05-21 21:55:34 +02:00
Lumpiasty	989732e1b5	move kokoro to separate deployment	2026-05-21 21:34:33 +02:00
Lumpiasty	ab438be629	fix tts model path	2026-05-21 21:11:29 +02:00
Lumpiasty	4556ca3c08	add ffmpeg for whisper	2026-05-21 20:58:56 +02:00
Lumpiasty	611f9f3886	add tts and sst to llama-swap and openwebui	2026-05-21 20:43:54 +02:00
Renovate	92bf792320	Update ghcr.io/mostlygeek/llama-swap Docker tag to unified-vulkan-2026-05-21	2026-05-21 17:40:41 +00:00
Lumpiasty	cfa3df6d1a	increase llama models PVC from 300Gi to 400Gi	2026-05-20 19:49:25 +02:00
Lumpiasty	c82f60e90a	switch text encoder to ponpoke/flux2-klein-4b-uncensored-text-encoder Q4_K_M	2026-05-20 17:50:06 +02:00
Lumpiasty	b41342be01	switch image model to FLUX.2-klein-4B (Apache 2.0, 4-step, unified gen+edit)	2026-05-20 16:49:30 +02:00
Lumpiasty	d3434a4102	remove unused qwen nothink chat template	2026-05-20 01:38:24 +02:00
Lumpiasty	de2822fee1	switch llama-swap to unified-vulkan image with FLUX.1-dev image generation ... - Update deployment to unified-vulkan-2026-05-19 (includes llama-server, sd-server, whisper-server in one image) - Fix binary paths: /app/llama-server -> llama-server (now on PATH) - Migrate groups -> matrix to allow FLUX to evict the always-on 0.8B model when image generation is requested - Add FLUX.1-dev Q4_K_S model via sd-server - Configure OpenWebUI image generation to use llama-swap sd-server - Update renovate versioning regex to treat all unified-vulkan date tags as patch updates for automerge	2026-05-20 01:11:57 +02:00
Lumpiasty	55ac337a63	enable MTP on MTP models	2026-05-18 20:31:57 +02:00
Renovate	cd8768de67	Update ghcr.io/mostlygeek/llama-swap Docker tag to v216	2026-05-18 17:59:16 +00:00
Lumpiasty	5397749a73	Merge pull request 'Update ghcr.io/mostlygeek/llama-swap Docker tag to v214-vulkan-b9174' (#288) from renovate/ghcr.io-mostlygeek-llama-swap-214.x into fresh-start ... Reviewed-on: #288	2026-05-18 17:57:20 +00:00
Lumpiasty	f3ad488bc8	add MTP version of Qwen3.6-35B	2026-05-18 19:42:48 +02:00
Renovate	8f51671c35	Update ghcr.io/mostlygeek/llama-swap Docker tag to v214-vulkan-b9174	2026-05-17 12:46:14 +00:00
Renovate	38ad78e69b	Update ghcr.io/mostlygeek/llama-swap Docker tag to v214	2026-05-17 02:01:24 +00:00
Renovate	2edcc0f4aa	Merge pull request 'Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9115' (#277) from renovate/ghcr.io-mostlygeek-llama-swap-211.x into fresh-start	2026-05-13 02:05:28 +00:00
Renovate	2af6065421	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9115	2026-05-13 02:05:24 +00:00
Renovate	b30d77436f	Update caddy Docker tag to v2.11.3	2026-05-13 02:05:22 +00:00
Renovate	e1ed09f938	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9102	2026-05-12 21:01:42 +00:00
Renovate	8269533c45	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9093	2026-05-12 02:05:31 +00:00
Renovate	cad7dab839	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9085	2026-05-11 02:01:10 +00:00
Renovate	5d18a56d3b	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9070	2026-05-10 02:01:10 +00:00
Renovate	eee1cd6a66	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9049	2026-05-09 02:01:14 +00:00
Renovate	1d7fa75b70	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9038	2026-05-08 02:01:09 +00:00
Renovate	028f4b1560	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9014	2026-05-06 02:01:06 +00:00
Renovate	2d1ac75c7c	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211-vulkan-b9010	2026-05-05 02:01:38 +00:00
Lumpiasty	0062ed03d2	Merge pull request 'Update ghcr.io/mostlygeek/llama-swap Docker tag to v211' (#255) from renovate/ghcr.io-mostlygeek-llama-swap-211.x into fresh-start ... Reviewed-on: #255	2026-05-04 17:43:05 +00:00
Lumpiasty	8d0c9f7a0d	increase llama ingress max request size	2026-05-04 17:53:07 +02:00
Renovate	9fdb7e6f7b	Update ghcr.io/mostlygeek/llama-swap Docker tag to v211	2026-05-04 02:01:17 +00:00
Renovate	1d1f782c56	Update ghcr.io/mostlygeek/llama-swap Docker tag to v210-vulkan-b8994	2026-05-03 02:04:18 +00:00
Renovate	3b55957687	Update ghcr.io/mostlygeek/llama-swap Docker tag to v210	2026-05-02 02:01:00 +00:00
Lumpiasty	8cbe2ef794	add abliterated versions of Qwen3.6-35B	2026-04-30 18:35:32 +02:00
Renovate	284c97acc8	Update ghcr.io/mostlygeek/llama-swap Docker tag to v208-vulkan-b8953	2026-04-30 02:00:56 +00:00
Renovate	4b1f047d9c	Update ghcr.io/mostlygeek/llama-swap Docker tag to v208-vulkan-b8943	2026-04-29 02:04:52 +00:00
Renovate	b1c98fbb2b	Update ghcr.io/mostlygeek/llama-swap Docker tag to v208	2026-04-28 02:00:58 +00:00
Renovate	f9367c3ea8	Update ghcr.io/mostlygeek/llama-swap Docker tag to v204-vulkan-b8864	2026-04-23 02:05:32 +00:00
Lumpiasty	b0f20de80b	qwen3.6 and cleanup of llama-swap config ... - Deleting unused models - Cleaned up, unified and fixed qwen3.5 sampling params to thinking and non-thinking params, no futrher differentiation - kv cache quant q4_0 everywhere	2026-04-23 00:43:37 +02:00
Renovate	0eae56bc4e	Update ghcr.io/mostlygeek/llama-swap Docker tag to v204	2026-04-22 02:01:04 +00:00
Lumpiasty	328b14ded7	add cpu version of Qwen3.5-35B-A3B	2026-04-18 23:21:52 +02:00
Lumpiasty	bc7eb5f0c5	Revert "switch llama from vulkan to rocm" ... This reverts commit 0e398706ab.	2026-04-18 16:42:02 +02:00
Lumpiasty	0e398706ab	switch llama from vulkan to rocm	2026-04-18 15:49:17 +02:00
Lumpiasty	480fb1c6d6	set bonsai model ctx to 64k	2026-04-18 15:48:30 +02:00
Renovate	b7a82eb9af	Update ghcr.io/mostlygeek/llama-swap Docker tag to v202	2026-04-18 02:01:09 +00:00
Lumpiasty	ae7f53c395	add bonsai model	2026-04-14 18:31:18 +02:00