-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Pull requests: THUDM/slime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[release] bump to v0.3.1
release
run-ci-megatron
#2252
opened Aug 4, 2026 by
zhuzilin
Contributor
Loading…
fix: cast gpu_id to int in sort_key to prevent lexicographic ordering
#2246
opened Jul 30, 2026 by
qq1243196045
Loading…
fix: restore args.ckpt_step after load_other_checkpoint
#2243
opened Jul 26, 2026 by
keepkeen
Loading…
fix: honor every eval.defaults key and restore per-dataset stop / min_new_tokens
#2242
opened Jul 26, 2026 by
keepkeen
Loading…
fix: restore negative dataset slice bounds (path@[-100:])
#2241
opened Jul 26, 2026 by
keepkeen
Loading…
fix: pool speculative-decoding metrics instead of averaging per-sample ratios
#2240
opened Jul 26, 2026 by
keepkeen
Loading…
fix: clear exec_and_wait's spawn lock between logical invocations
#2239
opened Jul 26, 2026 by
keepkeen
Loading…
fix: stop the fully-async rollout dropping completed groups
#2238
opened Jul 26, 2026 by
keepkeen
Loading…
fix: keep dataset order in filter_long_prompt for mixed multimodal data
#2237
opened Jul 26, 2026 by
keepkeen
Loading…
fix: don't overwrite an explicitly set --start-rollout-id
#2236
opened Jul 26, 2026 by
keepkeen
Loading…
fix: whiten advantages over the DP group that includes context parallel
#2235
opened Jul 26, 2026 by
keepkeen
Loading…
fix: pair --log-correct-samples rewards with the DP-local samples
#2234
opened Jul 26, 2026 by
keepkeen
Loading…
[Multimodal][Model] Make Qwen3.5-VL work with packed sequences
#2233
opened Jul 25, 2026 by
TobyYang7
Loading…
fix: avoid in-place mutation of param in MTP weight conversion (related to #2131)
#2227
opened Jul 21, 2026 by
botbikamordehai2-sketch
Loading…
Fix ref weights being broadcast on the first async update after resume
#2224
opened Jul 20, 2026 by
ishzgu
Loading…
[docker] backport output-gate slicing when query groups < TP
#2221
opened Jul 20, 2026 by
LLMShark
Loading…
fix(rm): deepscaler silently zeroes all rewards for non-thinking models
#2219
opened Jul 18, 2026 by
acmore
Loading…
fix(rollout): make dynamic refills granular
#2218
opened Jul 18, 2026 by
EazyReal
Contributor
Loading…
Fix tau-bench token deltas for reasoning templates
#2213
opened Jul 16, 2026 by
DongzhuoranZhou
Contributor
•
Draft
Support NemotronH hybrid Mamba+Attention+MoE training (e.g. Nemotron Nano-30B-A3B)
#2211
opened Jul 16, 2026 by
HelloWorldLTY
Contributor
Loading…
Fix partial rollout off-policy loss mask alignment
#2207
opened Jul 14, 2026 by
chengcuiping
Loading…
[Rollout] Add opt-in group-scoped session affinity
#2206
opened Jul 14, 2026 by
chengcuiping
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.