lobes-cli 0.90.2__tar.gz → 0.90.3__tar.gz

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project are documented here. The format is based on
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project
 adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.90.3] - 2026-10-18
+
+### Fixed
+
+- Mesh: plain `embedder` / `reranker` on a box that does not host them (the DGX Spark) answered 404 even though several members serve identical lanes, because their fingerprints advertised `quantization: unknown` and the strict pool rule never pools an unknown (#297). Every card profile now declares `quantization = "none"` for both pooling gears (the lanes pass no `--quantization`), rendered as `EMBED_QUANTIZATION=none` / `RERANK_QUANTIZATION=none` and added to `env.example`; `lobes doctor --fix` appends them to existing deployments. The strict rule itself is unchanged.
+
 ## [0.90.2] - 2026-10-18
 
 ### Changed

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/CLAUDE.md

@@ -977,7 +977,9 @@ rollback, restore the backup —, `...-accept-orin-embed.txt`). **UNVALIDATED:**
 everything beyond code retrieval — prose/docs/math, real image/video/audio
 retrieval (the probes were synthetic), MRL quality, cross-model agreement —
 is issue **#296**; the plain-`embedder`-on-the-Spark pooling finding is issue
-**#297** (a pre-existing strict-fingerprint rule, not caused by this shape). No
+**#297** (a pre-existing strict-fingerprint rule, not caused by this shape;
+fixed 2026-10-18 by declaring `quantization = "none"` for the embedder and
+reranker in every card profile, so their fingerprints carry a real value). No
 consumer is switched implicitly: `EIDETIC_EMBED_MODEL` / `COHERENCE_EMBED_MODEL`
 opt in by lane id and switching means re-embedding. See
 `docs/orin-embed-deployment.md`, `docs/embeddinggemma-2.md` and `lobes explain

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: lobes-cli
-Version: 0.90.2
+Version: 0.90.3
 Summary: lobes — run, assess, and switch the local vLLM model.
 Project-URL: Homepage, https://github.com/agentculture/lobes-cli
 Project-URL: Issues, https://github.com/agentculture/lobes-cli/issues

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/lobes/profiles/builtin/base.toml

@@ -90,12 +90,18 @@ feasible = true
 model = "Qwen/Qwen3-Embedding-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": the lane passes no --quantization, so the engine loads the
+# bf16 checkpoint as-is. Declared so the mesh fingerprint is a real value, not
+# "unknown", and identical members pool on a box that does not host them (#297).
+quantization = "none"
 
 [roles.reranker]
 feasible = true
 model = "Qwen/Qwen3-Reranker-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": as for the embedder above (#297).
+quantization = "none"
 
 # The opt-in `innereye` render tenant (ComfyUI, issue #82) is vetoed on an
 # unrecognised card for the same reason as muse/worker/associate: this

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/lobes/profiles/builtin/orin.toml

@@ -494,6 +494,10 @@ feasible = true
 model = "Qwen/Qwen3-Embedding-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": the lane passes no --quantization, so the engine loads the
+# bf16 checkpoint as-is. Declared so the mesh fingerprint is a real value, not
+# "unknown", and identical members pool on a box that does not host them (#297).
+quantization = "none"
 # attention_backend: overlaid from lobes.machines.get("orin") — TRITON_ATTN, a
 # conservative first-boot carry-over of Thor's sm_110 pooling divergence that
 # was NOT independently re-tested on sm_87. This gear booted healthy that way
@@ -504,6 +508,8 @@ feasible = true
 model = "Qwen/Qwen3-Reranker-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": as for the embedder above (#297).
+quantization = "none"
 # attention_backend + enforce_eager: overlaid from lobes.machines.get("orin") —
 # TRITON_ATTN + enforce_eager=true, the same carried-over Jetson safe-boot
 # choice. This gear booted healthy that way and its ordering probe passed

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/lobes/profiles/builtin/spark.toml

@@ -106,12 +106,18 @@ feasible = true
 model = "Qwen/Qwen3-Embedding-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": the lane passes no --quantization, so the engine loads the
+# bf16 checkpoint as-is. Declared so the mesh fingerprint is a real value, not
+# "unknown", and identical members pool on a box that does not host them (#297).
+quantization = "none"
 
 [roles.reranker]
 feasible = true
 model = "Qwen/Qwen3-Reranker-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": as for the embedder above (#297).
+quantization = "none"
 
 # --- innereye: the declared peak-GiB figure (issue #268, plan
 # innereye-lobes-hosts-comfyui, t6) --------------------------------------

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/lobes/profiles/builtin/thor.toml

@@ -141,6 +141,10 @@ feasible = true
 model = "Qwen/Qwen3-Embedding-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": the lane passes no --quantization, so the engine loads the
+# bf16 checkpoint as-is. Declared so the mesh fingerprint is a real value, not
+# "unknown", and identical members pool on a box that does not host them (#297).
+quantization = "none"
 # attention_backend: overlaid from the shared SM_110 trait — TRITON_ATTN
 # (the FlashInfer/FLASH_ATTN pooling path hangs on sm_110).
 
@@ -149,5 +153,7 @@ feasible = true
 model = "Qwen/Qwen3-Reranker-0.6B"
 gpu_mem_util = 0.06
 max_model_len = 8192
+# quantization "none": as for the embedder above (#297).
+quantization = "none"
 # attention_backend + enforce_eager: overlaid from the shared SM_110 trait —
 # TRITON_ATTN + enforce_eager=true (CUDA-graph capture is unstable here).

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/lobes/templates/fleet/env.example

@@ -149,6 +149,9 @@ EMBED_MAX_MODEL_LEN=8192
 # 0.06 load-tested 2026-06-19; 0.025 fails with "No available memory for the cache
 # blocks" (vLLM's pooling runner still reserves a cache-block budget).
 EMBED_GPU_MEM_UTIL=0.06
+# Declared for the mesh fingerprint only (the lane passes no --quantization): a real
+# value lets identical embedder members pool on a box that does not host one (#297).
+EMBED_QUANTIZATION=none
 # Internal URL the gateway uses to reach the embedding backend.
 EMBED_URL=http://vllm-embed:8000
 # Attention backend for the pooling runner. "auto" (the shipped default) is
@@ -215,6 +218,8 @@ RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 RERANK_MAX_MODEL_LEN=8192
 RERANK_GPU_MEM_UTIL=0.06
+# As EMBED_QUANTIZATION above (#297).
+RERANK_QUANTIZATION=none
 # Internal URL the gateway uses to reach the reranker backend.
 RERANK_URL=http://vllm-rerank:8000
 # Attention backend for the pooling runner — same "auto" sentinel/rationale as

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lobes-cli"
-version = "0.90.2"
+version = "0.90.3"
 description = "lobes — run, assess, and switch the local vLLM model."
 readme = "README.md"
 license = "Apache-2.0"

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/base.env

@@ -2,6 +2,7 @@ ASSOCIATE_FEASIBLE=false
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -17,5 +18,6 @@ PRIMARY_SERVED_NAME=Qwen/Qwen3.5-4B
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/orin.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_ATTENTION_BACKEND=TRITON_ATTN
@@ -29,5 +30,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-associate__base.env

@@ -2,6 +2,7 @@ ASSOCIATE_FEASIBLE=false
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 INNEREYE_FEASIBLE=false
@@ -13,5 +14,6 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-associate__orin.env

@@ -12,6 +12,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_FEASIBLE=false
@@ -27,5 +28,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-associate__spark.env

@@ -11,6 +11,7 @@ COMPOSE_PROFILES=associate
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 INNEREYE_DECLARED_PEAK_GIB=31.42
@@ -24,4 +25,5 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-associate__thor.env

@@ -12,6 +12,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 LOBES_BOOT_ORDER=associate
@@ -24,4 +25,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-cortex__base.env

@@ -2,6 +2,7 @@ ASSOCIATE_FEASIBLE=false
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -19,5 +20,6 @@ PRIMARY_SERVED_NAME=Qwen/Qwen3.5-4B
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-cortex__orin.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_ATTENTION_BACKEND=TRITON_ATTN
@@ -25,5 +26,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-cortex__spark.env

@@ -1,6 +1,7 @@
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -23,4 +24,5 @@ PRIMARY_SERVED_NAME=unsloth/Qwen3.8-27B-NVFP4
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-cortex__thor.env

@@ -2,6 +2,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 LOBES_BOOT_ORDER=embed,rerank
@@ -20,4 +21,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-decider__base.env

@@ -6,6 +6,7 @@ DECIDER_DOMAIN_MODELS=general=culture-dev/clef-27b-GPTQ-W4A16-g64@4daaa224c6dc55
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
 GEMMA2_EMBED_MEM_LIMIT=6g
@@ -20,5 +21,6 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-decider__orin.env

@@ -6,6 +6,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
@@ -24,5 +25,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-decider__spark.env

@@ -5,6 +5,7 @@ DECIDER_DOMAIN_MODELS=general=culture-dev/clef-27b-GPTQ-W4A16-g64@4daaa224c6dc55
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
 GEMMA2_EMBED_MEM_LIMIT=6g
@@ -21,4 +22,5 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-decider__thor.env

@@ -6,6 +6,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
 GEMMA2_EMBED_MEM_LIMIT=6g
@@ -21,4 +22,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-embed__base.env

@@ -3,6 +3,7 @@ COMPOSE_PROFILES=gemma2-embed
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
 GEMMA2_EMBED_MEM_LIMIT=6g
@@ -17,5 +18,6 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-embed__orin.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
@@ -21,5 +22,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-embed__spark.env

@@ -2,6 +2,7 @@ COMPOSE_PROFILES=gemma2-embed
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
 GEMMA2_EMBED_MEM_LIMIT=6g
@@ -18,4 +19,5 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-embed__thor.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GEMMA2_EMBED_BASE_URL=http://embed-gemma2-embed:8000
 GEMMA2_EMBED_MEM_LIMIT=6g
@@ -18,4 +19,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-lobe__base.env

@@ -2,6 +2,7 @@ ASSOCIATE_FEASIBLE=false
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -16,5 +17,6 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-lobe__orin.env

@@ -2,6 +2,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_ATTENTION_BACKEND=TRITON_ATTN
@@ -26,5 +27,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-lobe__spark.env

@@ -1,6 +1,7 @@
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -22,4 +23,5 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-lobe__thor.env

@@ -2,6 +2,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 LOBES_BOOT_ORDER=embed,rerank
@@ -19,4 +20,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-small__base.env

@@ -3,6 +3,7 @@ COMPOSE_PROFILES=minor
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -19,5 +20,6 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-small__orin.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_ATTENTION_BACKEND=TRITON_ATTN
@@ -24,5 +25,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-small__spark.env

@@ -2,6 +2,7 @@ COMPOSE_PROFILES=minor
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -20,4 +21,5 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/orin-small__thor.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 LOBES_BOOT_ORDER=embed,rerank
@@ -17,4 +18,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-innereye__base.env

@@ -2,6 +2,7 @@ ASSOCIATE_FEASIBLE=false
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -16,5 +17,6 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-innereye__orin.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_ATTENTION_BACKEND=TRITON_ATTN
@@ -28,5 +29,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-innereye__spark.env

@@ -2,6 +2,7 @@ COMPOSE_PROFILES=innereye
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -24,4 +25,5 @@ PRIMARY_FEASIBLE=false
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-innereye__thor.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_FEASIBLE=false
 INNEREYE_BASE_URL=http://comfyui:8188
@@ -21,4 +22,5 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-lobe__base.env

@@ -2,6 +2,7 @@ ASSOCIATE_FEASIBLE=false
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -21,5 +22,6 @@ PRIMARY_SPECULATIVE_CONFIG="'--speculative-config={\"method\":\"dspark\",\"model
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-lobe__orin.env

@@ -3,6 +3,7 @@ EMBED_ATTENTION_BACKEND=TRITON_ATTN
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 GATEWAY_READ_TIMEOUT=7200
 HAND_ATTENTION_BACKEND=TRITON_ATTN
@@ -28,5 +29,6 @@ RERANK_ENFORCE_EAGER=--enforce-eager
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B
 WORKER_FEASIBLE=false

{lobes_cli-0.90.2 → lobes_cli-0.90.3}/tests/goldens/shapes/spark-lobe__spark.env

@@ -1,6 +1,7 @@
 EMBED_GPU_MEM_UTIL=0.06
 EMBED_MAX_MODEL_LEN=8192
 EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
+EMBED_QUANTIZATION=none
 EMBED_SERVED_NAME=Qwen/Qwen3-Embedding-0.6B
 HAND_GPU_MEM_UTIL=0.06
 HAND_MAX_MODEL_LEN=32768
@@ -25,4 +26,5 @@ PRIMARY_SPECULATIVE_CONFIG="'--speculative-config={\"method\":\"dspark\",\"model
 RERANK_GPU_MEM_UTIL=0.06
 RERANK_MAX_MODEL_LEN=8192
 RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
+RERANK_QUANTIZATION=none
 RERANK_SERVED_NAME=Qwen/Qwen3-Reranker-0.6B