 Liangsheng Yin
|
5633ca8599
|
[Spec] Move prepare_for_draft to EagleDraftWorkerBase (#28105)
|
2026-06-12 17:42:43 -07:00 |
|
|
Liangsheng Yin
|
5f315c74da
|
[CI] Enforce modern stage=/runner_config= form for dispatchable test suites (#28108)
|
2026-06-12 17:32:54 -07:00 |
|
|
Liangsheng Yin
|
87554c7855
|
[Spec] Move draft-extend prep to EagleDraftWorkerBase; unify prepare_for_* names (#28093)
|
2026-06-12 16:44:04 -07:00 |
|
|
Liangsheng Yin
|
fd977adbd6
|
Fix PR-close cancellation skipping workflows beyond the first 30 (#27785)
|
2026-06-12 15:39:33 -07:00 |
|
|
Liangsheng Yin
|
caf59759ea
|
[Spec] Centralize dummy verify-input capture; add carries_draft_hidden_states (#28032)
|
2026-06-12 14:23:29 -07:00 |
|
|
Liangsheng Yin
|
a52ccd2179
|
[Spec] Install EagleDraftExtendInput as the V2 draft-extend spec_info (#24860)
|
2026-06-12 00:46:16 -07:00 |
|
|
Liangsheng Yin
|
e1164a6dfc
|
[Spec] Remove dead prepare_for_verify / prepare_extend_after_decode + extend-decode kernel (#27761)
|
2026-06-11 20:59:30 -07:00 |
|
|
|
7074704c0c
|
[Spec] Dedup post-verify mamba state commit into shared spec_utils helpers (#27966)
Co-authored-by: xbfs <xuebf1@lenovo.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-11 18:33:40 -07:00 |
|
|
Liangsheng Yin
|
3ffe72517f
|
[Spec] Remove the dead spec V1 scheduler paths (#27977)
|
2026-06-11 18:31:13 -07:00 |
|
|
Liangsheng Yin
|
c0480a88be
|
[Spec] Retire Spec V1 (#27964)
|
2026-06-11 16:15:15 -07:00 |
|
|
Liangsheng Yin
|
fee717f303
|
[Spec] Fold the DFLASH worker base into DFlashWorkerV2 on BaseSpecWorker (#27950)
|
2026-06-11 14:54:28 -07:00 |
|
|
Liangsheng Yin
|
acdb39edd2
|
[Spec] Remove the DFLASH V1 worker path (#27959)
|
2026-06-11 14:37:58 -07:00 |
|
|
Liangsheng Yin
|
df5055e00f
|
Bump spec logprob match delta for the bf16 eagle fixture (#27952)
|
2026-06-11 14:21:07 -07:00 |
|
|
Liangsheng Yin
|
1ac75c3463
|
[CI] Fix GB300 TestDummyWithSBO crash: disable NaN assert and coredump for dummy weights (#27955)
|
2026-06-11 14:17:03 -07:00 |
|
|
Liangsheng Yin
|
493bb6ae0d
|
Fix fp16 NaN flake in spec CI: bf16 eagle fixture; sanitize NaN logits in sampler (#27883)
|
2026-06-11 01:16:12 -07:00 |
|
|
Liangsheng Yin
|
16124fc9b2
|
[Metrics] Fix fwd_occupancy reading NaN on every decode log line; probe-free base-a (#27836)
|
2026-06-10 15:42:19 -07:00 |
|
|
Liangsheng Yin
|
5fefe91289
|
[Spec] NGRAMWorker on BaseSpecWorker; algo-owned verify-tree shape params (#27799)
|
2026-06-10 12:38:16 -07:00 |
|
|
Liangsheng Yin
|
d1895cb60d
|
[Spec] Extract move_accept_tokens_to_target_kvcache into spec_utils (#27764)
|
2026-06-09 21:55:26 -07:00 |
|
|
Liangsheng Yin
|
f332e52611
|
Add UT guarding per-request bookkeeping clock ownership (#27710)
|
2026-06-09 17:11:49 -07:00 |
|
|
|
decb88e0e3
|
Support spec v2 for Frozen-KV MTP; remove v1 worker (#27607)
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-09 15:30:20 -07:00 |
|
|
Liangsheng Yin
|
186f1e300a
|
[CI] Move JIT kernel tests + benchmarks to test/registered/jit; add in-package guard (#27644)
|
2026-06-09 12:37:39 -07:00 |
|
|
Liangsheng Yin
|
cae022aa88
|
[JIT] Reuse JIT kernel build cache across CI runs (#27605)
|
2026-06-08 22:14:48 -07:00 |
|
|
Liangsheng Yin
|
3fe6bc390b
|
[Spec] Naming cleanup: contiguous draft-loc kernel + accepted->accept (#27599)
|
2026-06-08 15:04:58 -07:00 |
|
|
Liangsheng Yin
|
b5c64b94d5
|
[Spec] Rename token resolver to _resolve_spec_v2_tokens; remove dead V1 helpers (#27552)
|
2026-06-08 14:42:21 -07:00 |
|
|
Liangsheng Yin
|
28c1a3cb45
|
[Spec] Deprecate Spec V1 (#25464)
|
2026-06-08 13:10:27 -07:00 |
|
|
Liangsheng Yin
|
57ea09badb
|
Fix NaN in triton EAGLE spec-v2 draft-extend CUDA graph at topk>1 (wrong qo_indptr stride) (#27545)
|
2026-06-08 02:28:48 -07:00 |
|
|
Liangsheng Yin
|
6365d6faee
|
[spec] Misc defensive guards for EAGLE draft KV indexing (#27486)
|
2026-06-07 21:27:46 -07:00 |
|
|
Liangsheng Yin
|
303757ccd8
|
[Attn] Fix aiter MLA verify kv_indices under-alloc + shared assert_buffer_fits guard (#27485)
|
2026-06-07 17:06:25 -07:00 |
|
|
Liangsheng Yin
|
f68c79675f
|
Support topk > 1 tree drafting for mamba/hybrid-linear models on spec v2 (#27463)
|
2026-06-07 17:04:09 -07:00 |
|
|
Liangsheng Yin
|
70db73afce
|
[Spec] Clamp multimodal pad sentinels in spec-v2 draft prefill embedding (#27512)
|
2026-06-07 17:00:49 -07:00 |
|
|
Liangsheng Yin
|
eab2e02fa0
|
[spec] Dedup draft kv_indices sizing into spec_utils helpers (#27475)
|
2026-06-07 00:42:29 -07:00 |
|
|
Liangsheng Yin
|
5e2e0d5b49
|
[spec] Make spec_utils module-importable: type-only imports under TYPE_CHECKING (#27484)
|
2026-06-07 00:01:32 -07:00 |
|
|
Liangsheng Yin
|
0ce3db3c0a
|
[Bug] Fix out-of-range token id crashing tp=1 VocabParallelEmbedding (#27482)
|
2026-06-06 23:00:17 -07:00 |
|
|
Liangsheng Yin
|
80eee2d92c
|
[Spec] Guard async-assert probes against None tensor (#27478)
|
2026-06-06 22:14:00 -07:00 |
|
|
Liangsheng Yin
|
066b4a2180
|
[core] Probe set_kv_buffer / set_mla_kv_buffer slot ids for OOB (#27459)
|
2026-06-06 19:51:09 -07:00 |
|
|
Liangsheng Yin
|
5160f7914e
|
Fix MLA EAGLE draft CUDA-graph kv_indices under-allocation for topk > 1 (#27460)
|
2026-06-06 16:28:34 -07:00 |
|
|
Liangsheng Yin
|
032c9efb46
|
Enable async-assert invariant probes by default in CI (#27461)
|
2026-06-06 16:23:21 -07:00 |
|
|
Liangsheng Yin
|
1c7acba579
|
[spec] Consolidate the per-decode KV alloc reserve into one helper (#27458)
|
2026-06-06 14:58:50 -07:00 |
|
|
Liangsheng Yin
|
4989d6691d
|
ci: show partition fit window as a date range in the step summary (#27457)
|
2026-06-06 14:39:36 -07:00 |
|
|
Liangsheng Yin
|
84ca0ffb8c
|
Spec v2 tree drafting (topk>1) with page_size>1 (#26972)
|
2026-06-06 12:00:27 -07:00 |
|
|
Liangsheng Yin
|
aa5213abb1
|
[debug] Register #27338 EAGLE draft kv_indices revert in pr_fix_toggle (#27428)
|
2026-06-06 00:30:13 -07:00 |
|
|
Liangsheng Yin
|
26b9053dcc
|
[Spec] Fix fa3 EAGLE draft-decode expand page_table scatter OOB for topk>1 + page_size>1 (#27360)
|
2026-06-06 00:24:34 -07:00 |
|
|
Liangsheng Yin
|
58a05d3dd2
|
[CI] Isolate CUDA coredump dir per run to fix tracker mis-attribution (#27344)
|
2026-06-05 21:31:22 -04:00 |
|
|
Liangsheng Yin
|
2c2a4f243a
|
[Bug] Fix EAGLE draft CUDA-graph kv_indices under-allocation for topk > 1 (#27338)
|
2026-06-05 16:22:04 -04:00 |
|
|
Liangsheng Yin
|
cd98d97037
|
Use level-1 (quiet) busy memory check in chunked-prefill and streaming tests (#27303)
|
2026-06-04 17:04:27 -04:00 |
|
|
Liangsheng Yin
|
687cfe9198
|
Enable runtime busy memory check for speculation topk>1 (#27228)
|
2026-06-04 16:46:20 -04:00 |
|
|
Liangsheng Yin
|
ef170c27b6
|
Add quiet mode for busy mem check (level 1: buffer + dump on leak) (#27238)
|
2026-06-04 04:31:57 -04:00 |
|
|
Liangsheng YinandAlison Shao
|
ac99794e64
|
Reland spec v2 tree drafting (eagle topk>1) with page_size==1 (#26866) (#26997)
Co-authored-by: Alison Shao <54658187+alisonshao@users.noreply.github.com>
|
2026-06-03 15:40:05 -04:00 |
|
|
Liangsheng Yin
|
578f232e5e
|
Fix trace_modules gate disabling default trace contexts (#27173)
|
2026-06-03 14:03:42 -04:00 |
|
|
Liangsheng Yin
|
f531bd7ff3
|
[Bug] Fix circular import in forward_batch_info from runtime cp_utils import (#27014)
|
2026-06-01 22:51:32 -07:00 |
|
|
Liangsheng Yin
|
54143264bf
|
ci: disable cross-job fast-fail for run_all_tests dispatch (#26990)
|
2026-06-01 18:32:41 -07:00 |
|
|
Liangsheng Yin
|
5e63200064
|
ci: full parallelism for run_all_tests dispatch (#26986)
|
2026-06-01 17:40:43 -07:00 |
|
|
Liangsheng Yin
|
f6d0beaca8
|
Revert "Support spec v2 tree drafting (eagle topk>1) with page_size==1" (#26981)
|
2026-06-01 17:16:44 -07:00 |
|
|
Liangsheng Yin
|
1d4ee060c2
|
Support spec v2 tree drafting (eagle topk>1) with page_size==1 (#26866)
|
2026-06-01 15:37:20 -07:00 |
|
|
Liangsheng Yin
|
dfa1af99f5
|
Fix kill_process_tree reap wait crashing on pidfd EINVAL (#26964)
|
2026-06-01 13:56:59 -07:00 |
|
|
Liangsheng Yin
|
1bff7a290f
|
Refactor EAGLE infer tests: shared fixture + kits + overlap matrix (#26871)
|
2026-06-01 03:55:01 -07:00 |
|
|
Liangsheng Yin
|
585baa97f7
|
[core] Compute token_type_ids in ForwardBatch.init_new (#26797)
|
2026-05-31 00:54:49 -07:00 |
|
|
Liangsheng Yin
|
9b4be9c574
|
[core] Compute dimensions/return_pooled_hidden_states in ForwardBatch.init_new (#26779)
|
2026-05-30 17:38:01 -07:00 |
|
|
Liangsheng Yin
|
282c46133f
|
[Scheduler] Defer prefill input_ids H2D to forward stream, unify resolve via future_map (#25945)
|
2026-05-30 02:58:13 -07:00 |
|
|
Liangsheng Yin
|
1c79015434
|
Drop dead ScheduleBatch return_routed_experts/return_indexer_topk fields (#26760)
|
2026-05-29 23:16:09 -07:00 |
|
|
Liangsheng Yin
|
1f850e67f2
|
[core] Fix crashes on the gpu_only spec_v2 path (#26738)
|
2026-05-29 19:12:03 -07:00 |
|
|
Liangsheng Yin
|
c2ac37dbcc
|
[Bug] ngram verify: keep batch.seq_lens_sum in sync after accept (#26753)
|
2026-05-29 18:00:11 -07:00 |
|
|
Liangsheng YinandQiaolin-Yu
|
6b5f0d0ccb
|
[core] Make spec_v2 seq_lens_cpu optional via backend needs_cpu_seq_lens; Triton opts out (#26128)
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
|
2026-05-29 13:00:32 -07:00 |
|
|
Liangsheng Yin
|
ed85bcf8c3
|
pin kernels<0.15 (#26704)
|
2026-05-29 01:46:57 -07:00 |
|
|
Liangsheng Yin
|
407106300e
|
test/disaggregation: dp-attention keeps total_tokens e2e, simpler LB algos -> unit tests (#26617)
|
2026-05-28 16:50:46 -07:00 |
|
|
Liangsheng Yin
|
ec78fa6518
|
test/registered: cleanup pure model e2e tests (moves, splits, dedup, kit) (#26610)
|
2026-05-28 15:41:46 -07:00 |
|
|
Liangsheng Yin
|
8e0ed75f2d
|
Remove dead fields and always-False plumbing across SB / FB / LogitsMetadata (#26551)
|
2026-05-28 03:15:04 -07:00 |
|
|
Liangsheng Yin
|
f143d54d78
|
Add env-var-conventions skill (#26553)
|
2026-05-28 02:58:37 -07:00 |
|
|
Liangsheng Yin
|
8dca6291c7
|
[CI] FA3: ascending cuda-graph capture to avoid varlen workspace IMA (#26532) (#26550)
|
2026-05-28 00:50:35 -07:00 |
|
|
Liangsheng Yin
|
686ef50672
|
Group ScheduleBatch and ForwardBatch fields by data-flow role (#26022)
|
2026-05-28 00:11:20 -07:00 |
|
|
Liangsheng Yin
|
216ed270e5
|
refresh resolve_seq_lens_cpu comments (#26463)
|
2026-05-27 00:51:43 -07:00 |
|
|
Liangsheng Yin
|
163b970127
|
[core] WAR barrier for overlap schedule buffer writes, without fwd occupancy cost (#26380)
|
2026-05-26 23:58:32 -07:00 |
|
|
Liangsheng Yin
|
1051a8456f
|
[core] Maintain req_pool_indices_cpu host mirror (like seq_lens_cpu) (#26425)
|
2026-05-26 18:59:54 -07:00 |
|
|
Liangsheng Yin
|
6076066e38
|
Add mooncake_tcp transfer backend (mooncake over TCP) (#26346)
|
2026-05-26 18:15:55 -07:00 |
|
|
Liangsheng Yin
|
ec6f8d61f7
|
[Spec] Async-assert probes across EAGLE/MTP; zero tgt_cache_loc (#26335)
|
2026-05-26 11:34:03 -07:00 |
|
|
Liangsheng Yin
|
7e6e5efe51
|
Revert "fix(tool_call): normalize non-standard JSON Schema types in tool params" (#26379)
|
2026-05-26 00:49:41 -07:00 |
|
|
Liangsheng Yin
|
1953565ba1
|
Signal CUDA coredumps to tracker issue (#26338)
|
2026-05-25 20:21:19 -07:00 |
|
|
Liangsheng Yin
|
8805f4cf16
|
Fail-fast on PD subprocess exit and scheduler exception (#26298)
|
2026-05-25 16:42:50 -07:00 |
|
|
Liangsheng Yin
|
3e67398a96
|
Zero req_pool_indices padding in cuda-graph populate (#26292)
|
2026-05-25 03:29:05 -07:00 |
|
|
Liangsheng Yin
|
850887dc63
|
[Spec] fix EAGLE v2 verify metadata init order on non-cuda-graph path (#26244)
|
2026-05-24 18:49:33 -07:00 |
|
|
Liangsheng Yin
|
ed179bf9b2
|
[dsv4] fix multi-step draft on non-cuda-graph path (#26239)
|
2026-05-24 17:04:18 -07:00 |
|
|
Liangsheng Yin
|
d7e3e54148
|
[Test] split test/registered/distributed/ into topic folders (#26240)
|
2026-05-24 17:02:07 -07:00 |
|
|
Liangsheng Yin
|
030bd5d3ed
|
[Test] test_session_latency: assert streaming tail/head stability (#26230)
|
2026-05-24 14:06:41 -07:00 |
|
|
Liangsheng Yin
|
1e59ed7443
|
compile _resolve_spec_extras gather kernels (#26129)
|
2026-05-23 02:34:41 -07:00 |
|
|
Liangsheng Yin
|
763174fa6c
|
FutureMap: debug-assert that gather sees a stashed value (#26108)
|
2026-05-22 13:10:57 -07:00 |
|
|
Liangsheng Yin
|
10751a4f0c
|
drop FutureIndices wrapper class (#26085)
|
2026-05-22 02:44:42 -07:00 |
|
|
Liangsheng Yin
|
c4b6b5ea1e
|
[core] step 2: drop seq_lens sentinel; SB maintains GPU as seq_lens_cpu mirror (#26020)
|
2026-05-22 00:12:51 -07:00 |
|
|
Liangsheng Yin
|
acb8310183
|
ci: self-heal $GITHUB_PATH/$GITHUB_ENV writes (#26037)
|
2026-05-21 21:28:43 -07:00 |
|
|
Liangsheng Yin
|
8b473aa0bc
|
[core] step 1: route non-spec seq_lens via FutureMap with per-mode bootstrap fixes (#25944)
|
2026-05-21 20:15:51 -07:00 |
|
|
Liangsheng Yin
|
7c02ca7882
|
cancel pr ci: cover closed-no-merge; widen workflows; rerun-test opt-in (#26035)
|
2026-05-21 19:38:24 -07:00 |
|
|
Liangsheng Yin
|
44ec2ee18d
|
[core] Unify output_tokens_buf in FutureMap (#25922)
|
2026-05-21 13:56:44 -07:00 |
|
|
Liangsheng Yin
|
c9a0e55eb5
|
[Spec] Polish FutureMap after #25879: rename callback, async guard, cleanup (#25962)
|
2026-05-21 13:56:22 -07:00 |
|
|
Liangsheng Yin
|
baeac179f7
|
[Spec] Route seq_lens through FutureMap; drop verify_done.wait (#25879)
|
2026-05-21 01:51:40 -07:00 |
|
|
Liangsheng Yin
|
1b3d8da827
|
cap API quota for runner-utilization / amd-ci-job-monitor (#25965)
|
2026-05-21 01:13:37 -07:00 |
|
|
Liangsheng Yin
|
512d164916
|
Address overlap future token map by request-pool index (#25862)
|
2026-05-20 16:34:00 -07:00 |
|
|
Liangsheng Yin
|
34d3e23232
|
spec_v2: consolidate seq_lens_cpu/sum maintenance into helper (#25818)
|
2026-05-20 04:42:26 -07:00 |
|
|
Liangsheng Yin
|
9b005d3608
|
disagg prebuilt: drop dead prepare_for_extend shift (#25819)
|
2026-05-20 04:39:47 -07:00 |
|
|
Liangsheng Yin
|
eccd5c8253
|
pr-test: schedule 3x -> 2x; fix extra gate skipped on schedule (#25872)
|
2026-05-20 03:58:54 -07:00 |
|
|
Liangsheng Yin
|
1bd4f94598
|
[Test] Add fwd_occupancy sanity kit (#25886)
|
2026-05-20 03:34:37 -07:00 |
|
|
Liangsheng Yin
|
614672fea5
|
[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831)
|
2026-05-20 01:58:48 -07:00 |
|