-
Notifications
You must be signed in to change notification settings - Fork 1.2k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
如何才能快速训练GLM 5.2
questionFurther information is requestedFurther information is requestedStatus: Open.#2324 In THUDM/slime;[Question] 什么时候支持ling3.0呢?
questionFurther information is requestedFurther information is requestedStatus: Open.#2314 In THUDM/slime;- Status: Open.#2299 In THUDM/slime;
- Status: Open.#2288 In THUDM/slime;
[Question/Performance] Full message history is re-tokenized on every coding-agent turn
questionFurther information is requestedFurther information is requestedStatus: Open.#2285 In THUDM/slime;[Bug] Qwen3.5 MoE online weight update sends ETP-sharded TEGroupedLinear weights without all-gather
bugSomething isn't workingSomething isn't workingStatus: Open.#2280 In THUDM/slime;- Status: Open.#2268 In THUDM/slime;
[Bug] Training/log-prob forward materializes full-vocab fp32 logits over the entire packed sequence → OOM for large-vocab, long multi-turn RL
bugSomething isn't workingSomething isn't workingStatus: Open.#2253 In THUDM/slime;[Question] Proposal: Add Train–Inference Consistency Data Collection to slime
questionFurther information is requestedFurther information is requestedStatus: Open.#2244 In THUDM/slime;[Question] 请问最新镜像(slimerl/slime:latest)支持A800吗
questionFurther information is requestedFurther information is requestedStatus: Open.#2232 In THUDM/slime;- Status: Open.#2231 In THUDM/slime;
- Status: Open.#2230 In THUDM/slime;