Skip to content

Pull requests: THUDM/slime

New pull request New
190 Open 1,486 Closed
190 Open 1,486 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

(fix): handle none/dict rewards in _compute_zero_std_metrics
#2157 opened Jul 1, 2026 by atoniolo76 Loading…
Support Qwen3.5 MoE INT4-QAT
#2156 opened Jun 30, 2026 by ShuZihan Loading…
4 of 9 tasks
fix(model_provider): add attention_backend and attention_softmax_in_fp32 to provider
#2155 opened Jun 30, 2026 by lyzustc Contributor Loading…
fix: support multi-head MTP weight mapping in MimoBridge (closes #2131)
#2154 opened Jun 30, 2026 by botbikamordehai2-sketch Loading…
1
fix(update_weight): bracket IPv6 master address in tcp:// init_method
#2151 opened Jun 30, 2026 by realJaydenCheng Loading…
fix: support fbox answers in math rewards
#2150 opened Jun 29, 2026 by wittsmith • Draft
[docker] Upgrade to sglang v0.5.14 run-ci-image
#2149 opened Jun 29, 2026 by zhuzilin Contributor Loading…
feat(p2p): add shard-level weight update with automatic broadcast fallback
#2146 opened Jun 29, 2026 by CalvinXKY Contributor Loading…
3 of 5 tasks
2
docs: fix dead examples/README link to low_precision
#2142 opened Jun 29, 2026 by aoshen02 Contributor Loading…
fix(examples): preserve geo3k response budget
#2140 opened Jun 27, 2026 by zhangdw156 Loading…
fix(examples): correct geo3k VLM default env
#2139 opened Jun 27, 2026 by zhangdw156 Loading…
docs(readme): add Dressage to Chinese ecosystem
#2138 opened Jun 27, 2026 by zhangdw156 Loading…
docs(examples): fix broken markdown links in rollout_buffer and examples
#2137 opened Jun 27, 2026 by CalvinXKY Contributor Loading…
docs(examples): list coding_agent_rl in examples/README
#2133 opened Jun 26, 2026 by aoshen02 Contributor Loading…
fix(mtp): support multi-head MTP loss logging (mtp-num-layers > 1)
#2132 opened Jun 26, 2026 by ZiyiTsang • Draft
Skip entropy gradient computation when entropy_coef == 0
#2130 opened Jun 25, 2026 by CSUN1997 Loading…
Support partial rollout resume in Search-R1 example
#2128 opened Jun 23, 2026 by OLIVER-XYP Loading…
Reduce entropy logging memory when entropy coef is zero
#2127 opened Jun 23, 2026 by none0663 Contributor Loading…
fix(data): prompt-length filtering crashes on VLM dataset with apply_chat_template
#2126 opened Jun 23, 2026 by Meihan-chen Loading…
Add test for megatron server run-ci-changed
#2123 opened Jun 23, 2026 by zhuzilin Contributor Loading…
fix(partial-rollout): cap max_new_tokens by prior response length
#2122 opened Jun 23, 2026 by none0663 Contributor Loading…
fix(retool): coerce list prompt to str in reward_func
#2120 opened Jun 23, 2026 by mvanhorn Loading…
1
fix(delta-sync): surface failed engine apply results instead of silently discarding them
#2119 opened Jun 22, 2026 by tanishkasinghhh Loading…
1
fix(rm_hub): grade the final ###Response segment in deepscaler reward
#2116 opened Jun 22, 2026 by SuperMarioYL Loading…
fix(rm_hub): guard deepscaler reward against a missing response
#2115 opened Jun 21, 2026 by vjsai Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.