coffee/DeepInfer
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepInfer.git synced 2026-10-28 14:57:09 +08:00
Code Issues Packages Projects Releases Wiki Activity
DeepInfer/tests/serve
History
whn09 d8f7a2e898 Neuron: PR #147 OpenAI server (+ /v1/completions, Neuron worker setup), offline bench, MoE fixes (#26, #27, #29) 
- serve/: the minimal OpenAI-compatible server of deepseek-ai/DeepInfer#147,
  with a Neuron worker setup (basic mode env, per-rank NeuronCore, fixed KV
  pool via --num-kv-blocks, no MTP lookahead) and a /v1/completions endpoint
  (prompt text or token ids, no chat template): what vllm bench serve
  --backend openai drives, as vllm-neuron#71's run_bench.py does.
- examples/neuron/bench_neuron.py: the same TTFT/TPOT matrix offline.
- static MoE: one packed fp32 all-gather instead of three (each 64-rank
  collective is ~2 ms of fixed latency a layer); a capacity-grouped expert
  path for prefill chunks (DEEPINFER_NEURON_MOE_CAPACITY, dense rerun on
  overflow; not yet validated on device).
- Sub-region timings at split() boundaries under DEEPINFER_NEURON_REGION_TIMING.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-23 16:23:28 +08:00
..
__init__.py Neuron: PR #147 OpenAI server (+ /v1/completions, Neuron worker setup), offline bench, MoE fixes (#26, #27, #29) 2026-10-23 16:23:28 +08:00
test_prompt_tokenizer.py Neuron: PR #147 OpenAI server (+ /v1/completions, Neuron worker setup), offline bench, MoE fixes (#26, #27, #29) 2026-10-23 16:23:28 +08:00