100 Commits
Author SHA1 Message Date
Mohammad Miadh AngkadandMohammad Angkad 78185f4b3f [Fix] [NVIDIA] modelopt-nvfp4: Read w13 global scales in the TRT-LLM [up, gate] order (#44858)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-20 07:38:45 +00:00
Mohammad Miadh AngkadandMohammad Angkad fdd53418a0 [CI] [NVIDIA] gb300: Drop Kimi-K2.5 and Qwen3.5 nightly tests (#45308)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-19 21:13:00 -07:00
Mohammad Miadh AngkadandMohammad Angkad 5b683d6b72 [Fix] test: Add logical_forward_mode to the KDA prefill-graph stand-in batch (#45218)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-19 21:06:10 -07:00
Mohammad Miadh AngkadandMohammad Angkad af856717c2 [Fix] mamba: Skip zero-width conv pools in the MTP verify scatter (#45212)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-19 19:23:17 -07:00
Mohammad Miadh AngkadandMohammad Angkad 7656ea0e74 [CI] python: Move the remaining CUDA build paths off Python 3.10 (#44393)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-19 14:29:00 -07:00
Mohammad Miadh AngkadandMohammad Angkad 377cd867fd [Perf] dsa: Route the k-pool indexer top-k through the top-k v2 kernel (#43775)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-19 09:49:39 +08:00
Mohammad Miadh AngkadandMohammad Angkad 9c7b338a19 [CI] jit-kernel: Honor continue_on_error on scheduled runs (#44645)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-16 22:29:01 -07:00
Mohammad Miadh AngkadandMohammad Angkad 2d8a05e719 [Test] attention: Fix replicated attention test missing full_attention_interval (#44602)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-16 22:28:37 -07:00
Mohammad Miadh AngkadandMohammad Angkad 3fc08b939a [Feat] server-args: Add --enable-hicache alias for --enable-hierarchical-cache (#44849)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-17 13:22:34 +08:00
Mohammad Miadh AngkadandMohammad Angkad 4fc86f73c2 [CI] glm5.2: Keep EOS in HiSparse needle test output (#44597)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-17 12:20:51 +08:00
Mohammad Miadh AngkadandMohammad Angkad 21791e7023 [CI] [NVIDIA] DSv4.1-Flash: Split GB300 accuracy test into one file per config (#44696)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-16 13:40:03 -07:00
Mohammad Miadh AngkadandMohammad Angkad 44be30d216 [Chore] deps: Bump FlashInfer to 0.7.2 (#44591)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-15 22:51:21 -07:00
Mohammad Miadh AngkadandMohammad Angkad 6231a617d3 [Test] diffusion: Load NVFP4 block scales through the weight loader in tests (#44595)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-16 10:56:27 +08:00
Mohammad Miadh AngkadandMohammad Angkad c82e8bd5fe [Fix] DeepSeek-V4.1: Align paged indexer score rows for DeepSelect decode (#44210)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-14 17:31:19 +08:00
Mohammad Miadh AngkadandMohammad Angkad 6daae9c98e [Perf] Bind scheduler CPUs to the GPU's NUMA node when memory policy is not permitted (#44023)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-14 00:01:32 -07:00
Mohammad Miadh AngkadandMohammad Angkad ff8d964cf5 [CI] glm5.2: Temporarily disable PD HiSparse+MTP B300 test (#44192)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-13 21:53:58 -07:00
Mohammad Miadh AngkadandMohammad Angkad 4f751da975 [Agents] Add a rule to prefer sgl-eval for accuracy evals (#44040)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-13 20:17:04 -07:00
Mohammad Miadh AngkadandMohammad Angkad 7f0434e4af [GLM-5.3-Flash] Drop the NextN layer from the KDA state pool (#44098)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-13 19:31:02 -07:00
Mohammad Miadh AngkadandMohammad Angkad 195cb7afb4 [CI] Use sgl-eval for GLM-5.3-Flash GSM8K tests (#43975)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-13 02:26:50 -07:00
Mohammad Miadh AngkadandMohammad Angkad 7bd41aec12 [CI] Remove Mistral Small 4 e2e test (#43973)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-12 20:14:22 -07:00
Mohammad Miadh AngkadandMohammad Angkad 06887827c7 [CI] Move tests that do not need GB300 off the per-PR GB300 suite (#43784)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-12 00:38:10 -07:00
Mohammad Miadh AngkadandMohammad Angkad 166b4ae7fc [Fix] Adapt to transformers 5.18 / 5.19 changes (#43688)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-11 23:24:57 -07:00
Mohammad Miadh AngkadandMohammad Angkad 130e11d50e [Deps] Bump FlashInfer to 0.7.1 (#43494)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-11 23:23:11 -07:00
Mohammad Miadh AngkadandMohammad Angkad bf703013f2 [Test] Re-anchor the VLM flashinfer throughput floor (#43762)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-11 21:34:50 -07:00
Mohammad Miadh AngkadandMohammad Angkad c640dc97ce [CI] Fix Kimi-Linear DCP PD test startup (#43598)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-10 16:53:54 -07:00
Mohammad Miadh AngkadandMohammad Angkad 16be9df25f [CI] Remove the GLM-5.3-Flash PTX KDA prefill nightly test (#43470)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-09 22:52:17 -07:00
Mohammad Miadh AngkadandMohammad Angkad 72eab59bf6 [GLM-5.3-Flash] Enable breakable prefill CUDA graph by default (#42845)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-10 02:41:02 +08:00
Mohammad Miadh AngkadandMohammad Angkad 5cbf949839 Fix torch.compile crash in fused gate-sigmoid-mul launcher (#43384)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-09 23:51:30 +08:00
Mohammad Miadh AngkadandMohammad Angkad 7578432c21 [LoRA][Test] Use the 0.9 ROUGE-L tolerance for the CUDA multi-LoRA batch test (#43297)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-09 01:51:01 -07:00
Mohammad Miadh AngkadandMohammad Angkad d8448d2e62 [CI] Re-enable GB300 (#43058)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-08 13:23:26 -07:00
Mohammad Miadh Angkad ac656ee79a [CI] Re-enable B300 (#42959) 2026-10-07 22:03:16 -07:00
Mohammad Miadh AngkadandMohammad Angkad 44d10eab5e [GLM-V] Shard the vision tower over the attention-TP group under DP attention (#42931)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-07 23:17:06 +08:00
Mohammad Miadh AngkadandMohammad Angkad f47d89564d [KDA] Default GLM-5-Next spec verify to the CuTe DSL KDA kernel (#42905)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-06 22:31:41 -07:00
Mohammad Miadh AngkadandMohammad Angkad 38bdf25f8d [Docker] Use uv-managed Python 3.12 and uv for all installs in the CUDA image (#42612)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-06 14:10:09 -07:00
Mohammad Miadh AngkadandMohammad Angkad 45db430530 [DSA] Fix pooled page table refresh for target verify CUDA graph replay (#42750)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-06 18:57:52 +08:00
Mohammad Miadh AngkadandMohammad Angkad 60878c3fba [CI] Temporarily disable B300 (#42704)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-05 22:27:54 -07:00
Mohammad Miadh AngkadandMohammad Angkad fcbbefa82a [GLM-5.3-Flash] Autotune MoE kernels at prefill sizes (#42693)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-05 21:04:54 -07:00
Mohammad Miadh AngkadandMohammad Angkad fea3c088a1 [CI] Temporarily disable GB300 (#42463)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-04 12:24:04 -07:00
Mohammad Miadh AngkadandMohammad Angkad 0bdd0cc8dc [Deps] Upgrade the CUDA PyTorch stack to 2.14 (#38641)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-04 00:48:02 -07:00
Mohammad Miadh AngkadandMohammad Angkad 7eb628612c [Fix] Publish the parallel config the CLIP attention test reads (#42460)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-04 00:44:51 -07:00
Mohammad Miadh AngkadandMohammad Angkad 1315d171a0 [Diffusion][CI] Add missing B200 Cirrascale runner E2E baselines (#42329)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-03 21:10:32 -07:00
Mohammad Miadh AngkadandMohammad Angkad c12bc635ca [CI] Install only userspace libgdrapi for GDRCopy (#42233)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-03 21:05:35 -07:00
Mohammad Miadh AngkadandMohammad Angkad 0e6d7eba5f [Fix] Count attention-DP ranks in one-batch bench running cap (#42331)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-03 21:04:27 -07:00
Mohammad Miadh AngkadandMohammad Angkad 3122b9c995 Update AOT kernels for Torch 2.14 (#42366)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-03 14:26:34 -07:00
Mohammad Miadh AngkadandMohammad Angkad 00bcc25f6c [HiCache] Fix DeepSeek-V4 storage backend crash from missing storage_format_tag (#42215)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-02 22:27:57 -07:00
Mohammad Miadh AngkadandMohammad Angkad d954c88a4f [Fix] Update stale source-patch match in dumper comparator e2e test (#42179)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-02 00:37:37 -07:00
Mohammad Miadh AngkadandMohammad Angkad e7d9c0299b [Docs] Keep the last CUDA 12 image tag fixed during install version bumps (#42201)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-02 00:17:13 -07:00
Mohammad Miadh AngkadandMohammad Angkad 42f2e4fcb7 [DSA] Stop forcing the per-step CPU seq_lens sync for the k-pool indexer (#41987)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-01 00:16:28 -07:00
Mohammad Miadh AngkadandMohammad Angkad 40e1bb0f36 [Docs] Add NVIDIA NVFP4 checkpoint to GLM-5.3-Flash cookbook (#41986)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-10-01 12:15:30 +08:00
Mohammad Miadh AngkadandMohammad Angkad 99c59a2ea6 Drop the GLM-5.3-Flash breakable prefill chunk-size pin (#41837)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-30 19:26:58 -07:00
547286bb5a [Deps] Bump transformers to 5.17.0 (#39012)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2026-09-30 12:52:02 -07:00
Mohammad Miadh AngkadandMohammad Angkad 036a3b3e14 [Test] Lower the SM120 NVFP4 KV GSM8K threshold to 0.60 (#41799)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-30 12:50:42 -07:00
Mohammad Miadh AngkadandMohammad Angkad eae808903f [Deps] Bump FlashInfer to 0.7.0.post1 (#40709)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-30 12:42:19 -07:00
Mohammad Miadh AngkadandMohammad Angkad 7b30ff26ee [CI] Evaluate the maintenance gate with github-script instead of jq (#41625)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-29 18:47:51 -07:00
Mohammad Miadh Angkadandhnyls2002 4885b563c3 [Test] Demote PD test RDMA openability check to a warning (#41681)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
2026-09-29 14:52:31 -07:00
Mohammad Miadh AngkadandMohammad Angkad e49d7fb170 Remove GLM-4.1V-9B-Thinking from encoder DP MMMU test (#41608)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-28 19:45:21 -07:00
Mohammad Miadh AngkadandMohammad Angkad cdbea5dccf [CI] Move DeepSelect into the attention kernel group to fix the namespace test (#41349)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-26 21:39:00 +08:00
Mohammad Miadh AngkadandMohammad Angkad 4bb645b8e2 [DSA] Fix the pooled-indexer breakable prefill bridge under DP attention (#41311)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-25 22:52:22 -07:00
Mohammad Miadh AngkadandMohammad Angkad 63d320c723 [DSA] Chunk the kpool indexer MQA logits by query rows under a free-memory budget (#40854)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-25 19:13:13 -07:00
cec70a4708 [Fix] Keep the target's DP sync slot in draft scopes (#41062)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2026-09-24 21:48:39 -07:00
Mohammad Miadh AngkadandMohammad Angkad 3fc7a669bf [CI] Move GLM-5.2 layer-split test to extra-b-test-8-gpu-b300 (#41207)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-24 21:25:48 -07:00
Mohammad Miadh AngkadandMohammad Angkad 86b3558b41 [Fix] Skip the DCP target-verify MLA kernel during FlashInfer autotune (#41138)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-24 11:19:28 -07:00
Mohammad Miadh Angkad bb1c98baa2 Fix TBO child batch missing dp_spec_prefill_coordination_applied (#41096) 2026-09-24 02:44:55 -07:00
Mohammad Miadh AngkadandMohammad Angkad 86cb4a0f97 [CI] Update GLM-5.3-Flash H200/B200 test args (#40862)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-22 23:21:04 -07:00
Mohammad Miadh AngkadandMohammad Angkad 7b977ce5dc [Fix] Decide the MoE padded-row bound from the layer scatter mode (#40672)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-22 16:02:17 -07:00
Mohammad Miadh AngkadandMohammad Angkad 4c81cd1b09 [KDA] Fix missing beta sigmoid in PTX prefill (#40685)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-21 23:24:38 -07:00
Mohammad Miadh Angkadandmmangkad e332e1b84e [Fix] Don't write conv state from the fused KDA verify kernel (#39524)
Co-authored-by: mmangkad <mohammad.angkad@radixark.ai>
2026-09-21 18:33:03 -07:00
11e661fd45 [Fix] Don't free the multi-CTAs KV counter the decode graphs captured (#39175)
Co-authored-by: mmangkad <mohammad.angkad@radixark.ai>
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-21 12:58:48 -07:00
Mohammad Miadh AngkadandMohammad Angkad 8d08dfdab7 [Fix] Add gigachat35 to the tool-call and reasoning parser name lists (#40554)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-21 16:34:43 +08:00
Mohammad Miadh Angkadandmmangkad 2fa6b94e34 [Perf] Fuse the glm5_next mHC attn->MLP boundary (#39200)
Co-authored-by: mmangkad <mohammad.angkad@radixark.ai>
2026-09-20 16:20:37 -07:00
Mohammad Miadh AngkadandMohammad Angkad 8923f4d779 [Test] Fix optimistic prefill disaggregation test after mamba radix cache removal (#40469)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-20 22:39:34 +08:00
Mohammad Miadh AngkadandMohammad Angkad 22f02cc339 [Test] Fix scheduler fixtures after prefill burst counting (#40411)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-20 00:08:04 -07:00
Mohammad Miadh AngkadandMohammad Angkad df0dc44931 [Fix] Forward SWA prealloc reclaim through the DSV4 HiSparse allocator (#40354)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-19 20:27:51 -07:00
Mohammad Miadh AngkadandMohammad Angkad c055dc6ff6 [CI] Check B200 NUMA mapping against sysfs numa_node (#40055)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-17 21:14:47 -07:00
Mohammad Miadh AngkadandMohammad Angkad 935cbf24ec Accept MXFP8 dispatch in FlashInfer A2A TRT-LLM MoE (#39613)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-15 19:23:15 -07:00
ddd4600197 [Fix] HiCache startup ImportError on the pinned kernel wheel (#39516)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
2026-09-14 22:31:19 -07:00
6c514ab025 Force reasoning mode for GLM-5.3 chat templates (#39227)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2026-09-15 13:16:26 +08:00
Mohammad Miadh Angkadandmmangkad 2fd835b9c1 [Fix] Don't write conv state from the fused KDA verify kernel (#39219)
Co-authored-by: mmangkad <mohammad.angkad@radixark.ai>
2026-09-13 21:26:57 -07:00
Mohammad Miadh AngkadandMohammad Angkad 4309c7ce19 Fix stale DSV4 indexer metadata names in the TopK v2 dispatch test (#39101)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-11 08:31:42 -07:00
Mohammad Miadh AngkadandMohammad Angkad ad5af539cd [CI] Trim DSV4 trtllm B200 tests (#39013)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-11 01:04:16 -07:00
Mohammad Miadh AngkadandMohammad Angkad 52c191da52 [Deps] Retire the CUDA 12 lane (#38404)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-10 16:58:09 -07:00
Mohammad Miadh AngkadandMohammad Angkad 613002281e [CI] Drop the GPTQ dynamic-config test for the deleted non-Marlin kernel (#38881)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-10 20:55:06 +08:00
Mohammad Miadh AngkadandMohammad Angkad dc2157dcd6 [JIT] Port the expert-pack MXFP4 kernels to load_jit and fix their launch limits (#38830)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-10 17:50:51 +08:00
Mohammad Miadh Angkad 8022505705 Revert "[CI] Temporarily disable GB300 tests" (#38842) 2026-09-10 02:41:15 -07:00
2092f6df05 [CI] Install helion 1.4.0 for the KDA Helion kernel tests (#38688)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Alison Shao <54658187+alisonshao@users.noreply.github.com>
2026-09-09 16:00:17 -07:00
Mohammad Miadh AngkadandMohammad Angkad 72d5c5bb73 [Kimi-K3] Accept fp32 routing weights in the fused MoE finalize (#38612)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-09 01:33:39 -07:00
Mohammad Miadh AngkadandMohammad Angkad a711785475 [Kernel] Drop the vendored dense BF16 GEMM port in favor of FlashInfer 0.6.18 (#38124)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-07 12:59:33 -07:00
Mohammad Miadh Angkad c5367fa964 [CI] Fix stale ServerArgs fake in chunked-SGMV LoRA test (#38315) 2026-09-07 04:25:12 -07:00
Mohammad Miadh Angkad cfa989b7af [CI] Fix stale CP-v1 mock patches in NextN mm-embed test (#38280) 2026-09-06 23:20:29 -07:00
Mohammad Miadh Angkad df2f34cca1 Drop stale test_mla_gluon_h12_fp8.py broken by aiter gluon rewrite (#38259) 2026-09-06 20:41:42 -07:00
Mohammad Miadh AngkadandMohammad Angkad 09daea94ac Support NoPE layers in the tokenspeed_mla FP8 prefill hook (#38152)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-05 16:51:04 -07:00
Mohammad Miadh AngkadandMohammad Angkad ca7b8efd87 [CI] Fix handle_platform_cp_compatibility reading legacy CP flags off the record (#37930)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-03 22:07:04 -07:00
Mohammad Miadh Angkad 3ad3f23ed5 [Comm] Drop the in-tree MNNVL CuTe DSL port in favor of FlashInfer 0.6.18 (#37206) 2026-09-03 21:49:48 -07:00
Mohammad Miadh AngkadandMohammad Angkad a5f07b1241 [CI] Build the Rust extensions for aarch64 too (#37820)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-03 19:54:08 -07:00
Mohammad Miadh AngkadandMohammad Angkad c1b4d535d7 [CI] Fix lint (#37895)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-03 18:37:50 -07:00
Mohammad Miadh Angkad 4372b8efa7 [1/N] Quantization Refactor: remove dead code and dedup the FP4 marlin helpers (#37552) 2026-09-03 14:22:31 -07:00
Mohammad Miadh Angkad 718bd39fe0 [Fix] DP attention: correct the decode->extend prefix off-by-one (#37505) 2026-09-02 16:14:16 -07:00
Mohammad Miadh Angkad d9ae1ebabd [CI] Preserve NCCL 2.30.7 after dependency installs (#37508) 2026-09-01 19:59:13 -07:00
Mohammad Miadh Angkad 03b33cbe5d [CI] Fix hybrid wrapper test fake missing kv_index_translator (#37374) 2026-09-01 00:55:05 -07:00
Mohammad Miadh Angkad e6f21cdadc [Cohere Command-A-Plus] Optimize decode and BCG capture on SM10X (#36624) 2026-08-31 19:37:47 -07:00