fix typos in example docs - #3
Merged
Merged
Conversation
rysaya
pushed a commit
to rysaya/slime
that referenced
this pull request
Aug 15, 2025
fix typos in example docs
guapisolo
pushed a commit
to guapisolo/slime_
that referenced
this pull request
Oct 16, 2025
Further modify tis
PopSoda2002
pushed a commit
that referenced
this pull request
Dec 19, 2025
…tory-r1xqo4 Remove FSDP rationale note from Chinese quick start
yueming-yuan
pushed a commit
to yueming-yuan/slime
that referenced
this pull request
Dec 29, 2025
Merged
jamescsq47
pushed a commit
to jamescsq47/slime
that referenced
this pull request
Mar 28, 2026
…epository-r1xqo4 Remove FSDP rationale note from Chinese quick start
jingshenghang
referenced
this pull request
in jingshenghang/slime
May 24, 2026
Combines SPEC §10.1 PRs #2-#5 into one atomic rewrite because all four touch the same single file (M1 decision: no sub-module split). Each PR's intent preserved as a distinct §section banner. PR #2 - §0 TOC docstring + §2 DATACLASSES (Turn, SubSession, SubSnapshot, Session) - Turn loses branch_kind/parent_id/parent_prefix_len/full_ids (0521 legacy) - Turn gains tito_masked: bool (U3) - SubSession gains num_aborts / last_finish_reason / tito_masked_turn_count - SubSnapshot adds finish_reason / num_aborts / tito_masked_turn_count - Session: active_subagent (flat) + completed_subagents + _emit_order (I6) - Session: num_aborts / num_aborts_this_turn / tito_*_turn_count - §3 PRIMITIVES & §4 STORE banners + Store.open_session(record_raw_dump=) PR #3 - §5 TRANSLATE adds verify_tito_for_turn (D2) - pure function: retokenize(decode(output_ids)) == output_ids - §6 ENGINE keeps AbortCoordinator + generate_with_abort_resume (P2 verbatim) PR #4 - §7 SEGMENTS rewrite - delete classifier triple: _classify_branch / _new_turn / 2-pass parent - delete _COMPACT_RESUME_MARKER text sniff + _SUMMARIZATION_MARKERS - delete _SubSession.subagent_stack nested stack -> flat active_subagent - new pick_target with nested-dispatch fail-safe (R2 CC3) - new classify_and_apply (4-condition is_append + pre_wipe snapshot) - new snapshot_subagent + pop_session_split (chronological replay of _emit_order) - segment meta key renamed kind -> segment_kind (U3 / R3) - U3: per-segment finish_reason + num_aborts + tito_masked_turns PR #5 - §8 HANDLER 15-step rewrite + §9 SHELL - _handle_messages: 380 lines -> ~140 lines, numbered 1-15 - step 12: I8 (n>0 guard) + I9 (abort skip TITO) + per-turn mask (only [-n:]) - Session.lock is sole sync primitive (P6); helpers never re-acquire (I3) - open_session(record_tree=) renamed to open_session(record_raw_dump=) - pop_session() single-segment API removed (list mode always on) - _export_raw_dump emits v4 schema (drops full_ids, adds tito_masked/etc) Tests (SPEC §7.1): 22 cases across 5 files, all passing - test_segments_classify.py - 7 cases (pre_wipe, nested fail-safe, etc.) - test_translate_tito.py - 6 cases incl. test_empty_turn_skip (I8 fix) and test_abort_skip_tito (I9) - test_engine_abort_resume.py - 3 cases (concatenate / max-attempts / budget) - test_session_lock.py - 2 cases (same-sid serialize, different sid) - test_pop_session_split.py - 4 cases (chronological, drain, U3 fields) - fixtures/README.md - schema doc
jingshenghang
referenced
this pull request
in jingshenghang/slime
May 25, 2026
Combines SPEC §10.1 PRs #2-#5 into one atomic rewrite because all four touch the same single file (M1 decision: no sub-module split). Each PR's intent preserved as a distinct §section banner. PR #2 - §0 TOC docstring + §2 DATACLASSES (Turn, SubSession, SubSnapshot, Session) - Turn loses branch_kind/parent_id/parent_prefix_len/full_ids (0521 legacy) - Turn gains tito_masked: bool (U3) - SubSession gains num_aborts / last_finish_reason / tito_masked_turn_count - SubSnapshot adds finish_reason / num_aborts / tito_masked_turn_count - Session: active_subagent (flat) + completed_subagents + _emit_order (I6) - Session: num_aborts / num_aborts_this_turn / tito_*_turn_count - §3 PRIMITIVES & §4 STORE banners + Store.open_session(record_raw_dump=) PR #3 - §5 TRANSLATE adds verify_tito_for_turn (D2) - pure function: retokenize(decode(output_ids)) == output_ids - §6 ENGINE keeps AbortCoordinator + generate_with_abort_resume (P2 verbatim) PR #4 - §7 SEGMENTS rewrite - delete classifier triple: _classify_branch / _new_turn / 2-pass parent - delete _COMPACT_RESUME_MARKER text sniff + _SUMMARIZATION_MARKERS - delete _SubSession.subagent_stack nested stack -> flat active_subagent - new pick_target with nested-dispatch fail-safe (R2 CC3) - new classify_and_apply (4-condition is_append + pre_wipe snapshot) - new snapshot_subagent + pop_session_split (chronological replay of _emit_order) - segment meta key renamed kind -> segment_kind (U3 / R3) - U3: per-segment finish_reason + num_aborts + tito_masked_turns PR #5 - §8 HANDLER 15-step rewrite + §9 SHELL - _handle_messages: 380 lines -> ~140 lines, numbered 1-15 - step 12: I8 (n>0 guard) + I9 (abort skip TITO) + per-turn mask (only [-n:]) - Session.lock is sole sync primitive (P6); helpers never re-acquire (I3) - open_session(record_tree=) renamed to open_session(record_raw_dump=) - pop_session() single-segment API removed (list mode always on) - _export_raw_dump emits v4 schema (drops full_ids, adds tito_masked/etc) Tests (SPEC §7.1): 22 cases across 5 files, all passing - test_segments_classify.py - 7 cases (pre_wipe, nested fail-safe, etc.) - test_translate_tito.py - 6 cases incl. test_empty_turn_skip (I8 fix) and test_abort_skip_tito (I9) - test_engine_abort_resume.py - 3 cases (concatenate / max-attempts / budget) - test_session_lock.py - 2 cases (same-sid serialize, different sid) - test_pop_session_split.py - 4 cases (chronological, drain, U3 fields) - fixtures/README.md - schema doc
HJSang
added a commit
to HJSang/slime
that referenced
this pull request
Jun 14, 2026
- #1 add --opsd-offload-teacher-logits to offload full-vocab teacher logits to CPU between forwards (moved back to device per micro-batch in the loss); keep the on-GPU view by default. Chunked JSD remains future work (THUDM#4, deferred). - THUDM#2 warn when privileged_info is empty/None (teacher==student context -> ~0 signal). - THUDM#3 repack teacher micro-batches by teacher lengths on the actor side, keeping the student's sample-to-rank assignment so response positions stay aligned (repack_micro_batches_by_length in dp_schedule.py; forward-only, per-rank). - THUDM#5 validate OPSD is not combined with --disable-compute-advantages-and-returns. - THUDM#6 skip loading the ref model under OPSD (never forwarded). - THUDM#7 descriptive error when a dataset row lacks the privileged-info field. Tests: add repack unit tests (coverage, token budget, oversized-sample-alone).
HJSang
added a commit
to HJSang/slime
that referenced
this pull request
Jun 14, 2026
#1 (critical): vocab-parallel log-softmax normalizer was all-reduced with an identity backward, under-counting the student-logit gradient by ~1/TP when tensor-parallel size > 1 (the global normalizer couples all ranks' log-probs, so its cotangent must be all-reduced). Add _VocabParallelAllReduceSumGradAllReduce (all-reduce forward AND backward) for the normalizer; keep identity-backward _VocabParallelAllReduceSum for the final replicated jsd reduction. Add a distributed (TP=2, gloo) test that shards the vocab and checks the JSD value and student gradient against the dense single-process reference (would fail under the old identity backward; a TP=1 test cannot catch it). THUDM#2 restore the actor as the live model via try/finally around the teacher forward so an OOM there can't leave teacher weights live for backup("actor"). THUDM#3 clone the [R, V] teacher response slice instead of keeping a view into the full [1, T_padded, V] microbatch buffer (frees the padded buffer; cheap, strictly better than the view). --opsd-offload-teacher-logits still offloads to CPU. THUDM#4 reject --opd-type=self with kl_coef!=0 or --use-kl-loss (OPSD is pure distillation; the ref model is intentionally not loaded). THUDM#5 log when auto-setting --loss-type=opsd instead of overwriting silently.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
script/run-glm4-9B.sh->scripts/run-glm4-9B.sh.The same with Qwen.