llama-stack-mirror/llama_stack/providers/utils/inference
Eric Huang e721ca9730 chore: introduce write queue for inference_store
# What does this PR do?
Adds a write worker queue for writes to inference store. This avoids overwhelming request processing with slow inference writes.

## Test Plan

Benchmark:
```
cd /docs/source/distributions/k8s-benchmark
# start mock server
python openai-mock-server.py --port 8000
# start stack server
uv run --with llama-stack python -m llama_stack.core.server.server docs/source/distributions/k8s-benchmark/stack_run_config.yaml
# run benchmark script
uv run python3 benchmark.py --duration 120 --concurrent 50 --base-url=http://localhost:8321/v1/openai/v1 --model=vllm-inference/meta-llama/Llama-3.2-3B-Instruct
```


Before:

============================================================
BENCHMARK RESULTS

Response Time Statistics:
  Mean: 1.111s
  Median: 0.982s
  Min: 0.466s
  Max: 15.190s
  Std Dev: 1.091s

Percentiles:
  P50: 0.982s
  P90: 1.281s
  P95: 1.439s
  P99: 5.476s

Time to First Token (TTFT) Statistics:
  Mean: 0.474s
  Median: 0.347s
  Min: 0.175s
  Max: 15.129s
  Std Dev: 0.819s

TTFT Percentiles:
  P50: 0.347s
  P90: 0.661s
  P95: 0.762s
  P99: 2.788s

Streaming Statistics:
  Mean chunks per response: 67.2
  Total chunks received: 122154
============================================================
Total time: 120.00s
Concurrent users: 50
Total requests: 1919
Successful requests: 1819
Failed requests: 100
Success rate: 94.8%
Requests per second: 15.16

Errors (showing first 5):
  Request error:
  Request error:
  Request error:
  Request error:
  Request error:
Benchmark completed.
Stopping server (PID: 679)...
Server stopped.


After:

============================================================
BENCHMARK RESULTS

Response Time Statistics:
  Mean: 1.085s
  Median: 1.089s
  Min: 0.451s
  Max: 2.002s
  Std Dev: 0.212s

Percentiles:
  P50: 1.089s
  P90: 1.343s
  P95: 1.409s
  P99: 1.617s

Time to First Token (TTFT) Statistics:
  Mean: 0.407s
  Median: 0.361s
  Min: 0.182s
  Max: 1.178s
  Std Dev: 0.175s

TTFT Percentiles:
  P50: 0.361s
  P90: 0.644s
  P95: 0.744s
  P99: 0.932s

Streaming Statistics:
  Mean chunks per response: 66.8
  Total chunks received: 367240
============================================================
Total time: 120.00s
Concurrent users: 50
Total requests: 5495
Successful requests: 5495
Failed requests: 0
Success rate: 100.0%
Requests per second: 45.79
Benchmark completed.
Stopping server (PID: 97169)...
Server stopped.
2025-09-10 11:50:06 -07:00
..
__init__.py chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
embedding_mixin.py fix: Make SentenceTransformer embedding operations non-blocking (#3335) 2025-09-04 13:58:41 -04:00
inference_store.py chore: introduce write queue for inference_store 2025-09-10 11:50:06 -07:00
litellm_openai_mixin.py chore: indicate to mypy that InferenceProvider.batch_completion/batch_chat_completion is concrete (#3239) 2025-08-22 14:17:30 -07:00
model_registry.py refactor(logging): rename llama_stack logger categories (#3065) 2025-08-21 17:31:04 -07:00
openai_compat.py refactor(logging): rename llama_stack logger categories (#3065) 2025-08-21 17:31:04 -07:00
openai_mixin.py refactor(logging): rename llama_stack logger categories (#3065) 2025-08-21 17:31:04 -07:00
prompt_adapter.py refactor(logging): rename llama_stack logger categories (#3065) 2025-08-21 17:31:04 -07:00