docs(dev): Ornith FP8 vLLM 인벤토리를 기록한다
This commit is contained in:
parent
70c99c17a8
commit
9578744c35
1 changed files with 100 additions and 1 deletions
|
|
@ -1,6 +1,6 @@
|
|||
test_env: dev
|
||||
profile: dev-runtime-provider-pool
|
||||
last_updated_at: "2026-07-09"
|
||||
last_updated_at: "2026-07-12"
|
||||
|
||||
source:
|
||||
remote_runner:
|
||||
|
|
@ -151,6 +151,71 @@ model:
|
|||
base_url: http://192.168.0.91:8002/v1
|
||||
served_model: nvidia/diffusiongemma-26B-A4B-it-NVFP4
|
||||
reasoning: false
|
||||
current_runtime_status: stopped_2026_07_12_replaced_by_ornith_direct_fp8
|
||||
spark_ornith_direct_profile:
|
||||
observed_at: "2026-07-12"
|
||||
provider: ornith-direct
|
||||
status: active_direct_pi_provider_not_part_of_iop_provider_pool
|
||||
family: spark_ornith
|
||||
api: openai-completions
|
||||
base_url: http://192.168.0.91:8002/v1
|
||||
model_id: ornith:35b
|
||||
display_name: Ornith 1.0 35B FP8 Direct vLLM
|
||||
context_window: 262144
|
||||
max_tokens: 32768
|
||||
reasoning: true
|
||||
endpoint_policy: Pi connects directly to the GX10/Spark vLLM OpenAI-compatible endpoint; this profile bypasses IOP Edge routing and does not participate in the dev Qwen provider pool.
|
||||
api_key_value_tracked: false
|
||||
pi_current_default_at_observation:
|
||||
default_provider: ornith-direct
|
||||
default_model: ornith:35b
|
||||
default_api: openai-completions
|
||||
default_base_url: http://192.168.0.91:8002/v1
|
||||
qwen_parameter_alignment:
|
||||
pi_context_window: 262144
|
||||
pi_max_tokens: 32768
|
||||
context_match: matches the dev Qwen Pi contextWindow and vLLM max_model_len value
|
||||
output_budget_match: matches the dev Qwen Pi maxTokens/default_max_tokens value
|
||||
runtime_summary:
|
||||
host: toki@192.168.0.91
|
||||
container_name: iop-vllm-ornith35b-fp8
|
||||
docker_image: vllm/vllm-openai:nightly-aarch64
|
||||
endpoint: http://192.168.0.91:8002/v1
|
||||
hf_model: deepreinforce-ai/Ornith-1.0-35B-FP8
|
||||
served_model_name: ornith:35b
|
||||
quantization: fp8
|
||||
vllm_quantization_backend: compressed-tensors
|
||||
dtype: bfloat16
|
||||
max_model_len: 262144
|
||||
max_num_seqs: 2
|
||||
gpu_memory_utilization: 0.50
|
||||
enable_prefix_caching: true
|
||||
enable_auto_tool_choice: true
|
||||
tool_call_parser: qwen3_xml
|
||||
reasoning_parser: qwen3
|
||||
trust_remote_code: true
|
||||
language_model_only: true
|
||||
model_load_memory_gib: 34.43
|
||||
available_kv_cache_memory_gib: 21.33
|
||||
gpu_kv_cache_tokens: 1087640
|
||||
max_concurrency_for_262144_token_requests: 4.15
|
||||
official_4bit_gguf_status:
|
||||
hf_model: deepreinforce-ai/Ornith-1.0-35B-GGUF
|
||||
file: ornith-1.0-35b-Q4_K_M.gguf
|
||||
status: not_active
|
||||
reason: current vLLM GGUF plugin path exposed /v1/models but failed semantic generation smoke; active working runtime uses the official FP8 vLLM model instead.
|
||||
smoke:
|
||||
english_final_answer: passed
|
||||
korean_final_answer: passed
|
||||
pi_direct_cli: passed
|
||||
output_throughput:
|
||||
method: completion_tokens divided by end-to-end request wall time, max_tokens=768
|
||||
average_completion_tok_s: 29.8
|
||||
run_completion_tok_s:
|
||||
- 29.65
|
||||
- 30.62
|
||||
- 29.15
|
||||
note: vLLM logs showed aggregate generation throughput around 50-61 tok/s with two running requests.
|
||||
separation_note: This host Pi default profile is the dev Qwen3.6 provider-pool profile. Keep dev-corp Gemma4 under agent-test/dev-corp/inventory.yaml and do not copy Gemma4 parser/template/runtime settings into this Qwen profile.
|
||||
content_completion_policy:
|
||||
enforce_min_max_tokens: true
|
||||
|
|
@ -362,6 +427,40 @@ nodes:
|
|||
reasoning_parser: qwen3
|
||||
default_chat_template_kwargs:
|
||||
enable_thinking: true
|
||||
direct_providers:
|
||||
- id: ornith-direct
|
||||
family: spark_ornith
|
||||
type: vllm
|
||||
endpoint: http://192.168.0.91:8002/v1
|
||||
served_model: ornith:35b
|
||||
upstream_model: deepreinforce-ai/Ornith-1.0-35B-FP8
|
||||
status: active_direct_pi_provider_not_iop_routed
|
||||
pi_model_parameters:
|
||||
context_window: 262144
|
||||
max_tokens: 32768
|
||||
reasoning: true
|
||||
runtime:
|
||||
container_name: iop-vllm-ornith35b-fp8
|
||||
docker_image: vllm/vllm-openai:nightly-aarch64
|
||||
port_mapping: 0.0.0.0:8002->8000
|
||||
quantization: fp8
|
||||
vllm_quantization_backend: compressed-tensors
|
||||
dtype: bfloat16
|
||||
max_model_len: 262144
|
||||
max_num_seqs: 2
|
||||
gpu_memory_utilization: 0.50
|
||||
enable_prefix_caching: true
|
||||
enable_auto_tool_choice: true
|
||||
tool_call_parser: qwen3_xml
|
||||
reasoning_parser: qwen3
|
||||
trust_remote_code: true
|
||||
language_model_only: true
|
||||
model_load_memory_gib: 34.43
|
||||
available_kv_cache_memory_gib: 21.33
|
||||
gpu_kv_cache_tokens: 1087640
|
||||
max_concurrency_for_262144_token_requests: 4.15
|
||||
average_completion_tok_s: 29.8
|
||||
replacement_note: DiffusionGemma direct vLLM on this endpoint was stopped; Ornith is served from the official FP8 Hugging Face release, not the 4-bit GGUF build.
|
||||
- id: onexplayer-lemonade-node
|
||||
alias: onexplayer-lemonade
|
||||
role: lemonade-provider
|
||||
|
|
|
|||
Loading…
Reference in a new issue