github-featured / lightseekorg--tokenspeed

分支列表

main

0ba6b6aab7 · perf(mla): add opt-in packed Q decode for FP8 and FP16 (#1512) · 最后更新于 2026-09-12 09:04:01 +00:00

users/qedawkins/kimi-k3-higher-batch 01589f33f9 · perf(moe): reduce Kimi K3 grouped decode padding · 最后更新于 2026-08-24 19:01:30 +00:00 frostbyte_neo	242 6	ZIP TAR.GZ
feat/amd-kda-mtp-verify 2e4014ee41 · feat(kda): add AMD fused MTP verification · 最后更新于 2026-08-24 13:23:14 +00:00 frostbyte_neo	226 1	ZIP TAR.GZ
perf/tsmla-block-decode f7d22cd9b5 · feat(mla): serve a block drafter from the CuteDSL MLA backend · 最后更新于 2026-08-24 02:49:18 +00:00 frostbyte_neo	226 1	ZIP TAR.GZ
perf/prep-tape-input-tail 64a2b0ea3e · fix(metadata): stage a tape's registers through a per-call pinned block · 最后更新于 2026-08-23 19:06:05 +00:00 frostbyte_neo	231 2	ZIP TAR.GZ
hongtaoc/attnres-no-t-limit-103120 9d258bf8c7 · Merge branch 'main' into hongtaoc/attnres-no-t-limit-103120 · 最后更新于 2026-08-23 16:51:27 +00:00 frostbyte_neo	230 3	ZIP TAR.GZ
test/kimi-k3-pdsim-bench 5de4bd6980 · test(kimi-k3): dedup first turns and guard shrunken samples in pd_sim · 最后更新于 2026-08-23 14:23:46 +00:00 frostbyte_neo	232 2	ZIP TAR.GZ
perf/amd-kda-prefill-tuning 94604367aa · perf(gfx1250): fill the WMMA tile in the KDA state scan · 最后更新于 2026-08-23 10:36:08 +00:00 frostbyte_neo	232 4	ZIP TAR.GZ
borontion/amd-dsv4-1 9ba79c95a2 · fix(dsv4): reset stale decode plans · 最后更新于 2026-08-23 09:47:30 +00:00 frostbyte_neo	239 42	ZIP TAR.GZ
feat/chunk-pp-event-loop-cohesion df3183f0da · feat(runtime): prefill chunk pipeline + event-loop cohesion refactor · 最后更新于 2026-08-23 09:26:35 +00:00 frostbyte_neo	233 1	ZIP TAR.GZ
ts2/kda-commit-launch 263bcfc1d7 · perf(kda): size the batched commit launches from the grid they actually have · 最后更新于 2026-08-23 09:16:11 +00:00 frostbyte_neo	238 1	ZIP TAR.GZ
hongtaoc/k3-split-shared-rs 4d868c3492 · docs(k3): document split shared shard contract · 最后更新于 2026-08-23 07:50:00 +00:00 frostbyte_neo	234 5	ZIP TAR.GZ
perf/k3-kda-payload-copy 35594c74f2 · Merge branch 'main' into perf/k3-kda-payload-copy · 最后更新于 2026-08-23 01:55:29 +00:00 frostbyte_neo	239 2	ZIP TAR.GZ
ts2/kda-triton-tuning 7ff10897c8 · Merge branch 'main' into ts2/kda-triton-tuning · 最后更新于 2026-08-23 01:41:26 +00:00 frostbyte_neo	239 2	ZIP TAR.GZ
ts2/k3-aime26-64k 8cfe3d7984 · ci(k3): give the Slurm aime26 gates the budget their context window allows · 最后更新于 2026-08-22 23:50:23 +00:00 frostbyte_neo	246 1	ZIP TAR.GZ
codex/disable-smg-load-monitoring efcadf1adc · fix(cli): disable smg load monitoring by default · 最后更新于 2026-08-22 16:48:36 +00:00 frostbyte_neo	244 1	ZIP TAR.GZ
codex/fix-load-communicator-race ef0cf55ac4 · style(runtime): format scheduler communicator · 最后更新于 2026-08-22 16:48:01 +00:00 frostbyte_neo	244 2	ZIP TAR.GZ
feat/k3-dspark-torchspec-draft-recreated 4b9766f6cc · chore: merge main and drop CI test changes · 最后更新于 2026-08-22 09:32:38 +00:00 frostbyte_neo	246 12	ZIP TAR.GZ
k3-decode-route-shared 6d83175f85 · fix(gemm): admit sm100 to the measured decode route · 最后更新于 2026-08-22 04:22:40 +00:00 frostbyte_neo	250 5	ZIP TAR.GZ
perf/mla-write-locations 627f6474bb · refactor(attn): import Triton through the vendored facade · 最后更新于 2026-08-22 02:07:35 +00:00 frostbyte_neo	250 3	ZIP TAR.GZ
ts2/kda-vmajor-nv 29047cd9fa · perf(kda): strong-form V-major replay tiles, thin replay fold, launch params · 最后更新于 2026-08-21 19:43:39 +00:00 frostbyte_neo	256 2	ZIP TAR.GZ

... 6 7 8 9 10 ...

默认分支

分支列表