Repository navigation

S26-E0.1: efficiency evaluation (bare vs yeto, verl and Miles) - #281

Closed

michaellchung wants to merge 12 commits into

s25-finalfrom

s26-e01-effeval

Closed

S26-E0.1: efficiency evaluation (bare vs yeto, verl and Miles)#281
michaellchung wants to merge 12 commits into
s25-finalfrom
s26-e01-effeval

Commits on Oct 20, 2026
- tools/eval: add efficiency evaluation (bare vs yeto, verl and Miles)
  
  chowhsu
  and
  claude
  committed
  5a01732
- tools/eval: bare Miles trains with unfused attention (match yeto generic recipe; TE flash fails on sm86)
  
  chowhsu
  and
  claude
  committed
  261ba2e
- tools/eval: yeto+verl async arm passes the staleness-2 TIS algorithm spec
  
  chowhsu
  and
  claude
  committed
  c3c9d09
- tools/eval: bare verl arms run the unpatched fork; async uses merged LoRA and /dev/shm NCCL host buffers
  
  chowhsu
  and
  claude
  committed
  63dc064
- tools/eval: parse bare verl fully_async rows by training step; rates over rounds that report the value
  
  chowhsu
  and
  claude
  committed
  052c31e
- tools/eval: bare Miles arms do not shuffle prompts (yeto's Miles argv does not)
  
  chowhsu
  and
  claude
  committed
  c9245e5
- verl adapter: fully_async keeps NCCL host buffers on /dev/shm in every Ray worker
  
  chowhsu
  and
  claude
  committed
  73442ad
- tools/eval: read the yeto+Miles launcher exit code into the parsed run
  
  chowhsu
  and
  claude
  committed
  0122f4e
- miles adapter: opt-in gradient-accumulation fusion; generic recipe trains without dropout
  
  chowhsu
  and
  claude
  committed
  e0f833d
- tools/eval: yeto+Miles arm takes the bare Miles recipe settings
  
  chowhsu
  and
  claude
  committed
  6a4263e
- tools/eval: read only the run's own tapes (skip the repo copy and the store)
  
  chowhsu
  and
  claude
  committed
  ff893bc
- tools/eval: verl fully_async generation time from the rollouter, else missing
  
  chowhsu
  and
  claude
  committed
  ba17953

Commits

Commits on Oct 20, 2026