-
Notifications
You must be signed in to change notification settings - Fork 895
Pull requests: THUDM/slime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
perf(ppo): gather response/loss-mask rows before log-prob+entropy CE (supersedes #2011)
#2076
opened Jun 14, 2026 by
Mantissagithub
Loading…
Support Qwen3.5-VL (dense + MoE) via Megatron-Bridge
#2075
opened Jun 14, 2026 by
demouo
Contributor
Loading…
feat(rollouts) external rollouts endpoint with publish-only weight sync
#2071
opened Jun 12, 2026 by
jvmncs
Loading…
4 tasks done
fix(agent): reuse a pooled SGLang client across turns and retry once on pre-connect connector errors
#2069
opened Jun 12, 2026 by
EazyReal
Loading…
fix(sglang): authenticate engine control-plane and router calls
#2068
opened Jun 12, 2026 by
EazyReal
Loading…
[megatron] don't re-assert no_sync_func every step with overlap_grad_reduce
#2066
opened Jun 12, 2026 by
HaozheZhang6
•
Draft
fix(dp_schedule): drop trailing rollouts when the aligned micro-batch target exceeds the sample count
#2065
opened Jun 12, 2026 by
EazyReal
Loading…
fix(metrics): make compute_pass_rate ragged-safe for over-sampled batches
#2064
opened Jun 12, 2026 by
EazyReal
Loading…
fix(agent): render OpenAI tool-call arguments as a mapping for chat templates
#2063
opened Jun 12, 2026 by
EazyReal
Loading…
fix(grpo): correct reward attribution for fanned rollouts — full reward per segment + count each rollout once
#2062
opened Jun 12, 2026 by
EazyReal
Loading…
fix(rollout): apply rollout sample filter in the rollout manager
#2061
opened Jun 12, 2026 by
EazyReal
Loading…
feat(loss): add
--pg-loss-divisor: first-class constant-divisor pg_loss normalization (Dr.GRPO)
#2060
opened Jun 12, 2026 by
EazyReal
Loading…
(fix) retry transient Ray ActorUnavailableError during rollout engine bringup
#2059
opened Jun 12, 2026 by
EazyReal
Loading…
[Feature] Mopd (Multi-Teacher On-Policy distillation) supported
#2051
opened Jun 11, 2026 by
leoyuppieqnew
•
Draft
fix(parsing): strip trailing EOS token from body_text after tool/reasoning parsing for code agent rl
#2049
opened Jun 10, 2026 by
none0663
Contributor
Loading…
support --num-workers for dataset parallel loading
#2048
opened Jun 10, 2026 by
demouo
Contributor
Loading…
feat(rollout): add rollout-side torch profiler trigger via sglang
#2038
opened Jun 9, 2026 by
niu0421
Loading…
fix(rollout): drain generation before offload memory release
#2015
opened Jun 4, 2026 by
EazyReal
Loading…
fix(colocate): derive num_gpus_per_node from actor_num_gpus_per_node
#2012
opened Jun 3, 2026 by
aoshen02
Contributor
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.