 Mick
|
578e936d8d
|
[diffusion] feat: persist torch.compile inductor/triton cache across restarts (#28205)
|
2026-06-15 13:34:19 +08:00 |
|
|
|
07b9108348
|
[Diffusion] FLUX: fuse FeedForward GELU into up-proj GEMM (cublasLt epilogue) (#28166)
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-15 13:00:26 +08:00 |
|
|
Prajjandprajjwal1
|
441b75ee69
|
[quantization] NVFP4 MoE: split fused w13 gate/up global scales (#27588)
Co-authored-by: prajjwal1 <prajjwal1@protonmail.com>
|
2026-06-14 21:18:36 -07:00 |
|
|
Ryan Zzzandzhujunyu
|
ce9fad7196
|
[Bugfix][DeepSeek-V4] Fix Spec V2 Draft Input ID Dtype for DP Collectives (#28043)
Co-authored-by: zhujunyu <zhujunyu.666@bytedance.com>
|
2026-06-14 21:11:53 -07:00 |
|
|
weireweire
|
bf38a0b03d
|
Fix disaggregated decode load token accounting (#25736)
|
2026-06-15 11:37:41 +08:00 |
|
|
|
0417951a86
|
[Bug Fix] Validate tokenizer-dependent features with skip_tokenizer_init (#27882)
Co-authored-by: Randall <randall@iterationlab.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-14 20:07:52 -07:00 |
|
|
Zyann
|
37505eca27
|
feat: report multimodal (image/audio/video) token counts in usage.prompt_tokens_details (#27122)
|
2026-06-15 11:04:10 +08:00 |
|
|
Mohammad Miadh Angkad
|
69b02ea68a
|
[Distributed] Guard torch symm mem all-reduce sizes (#24548)
|
2026-06-14 18:28:57 -07:00 |
|
|
Xinyuan Tong
|
1a66059c4e
|
[Spec] Restore index_share_for_mtp_iteration in EAGLE V2 draft worker (#28192)
|
2026-06-14 18:01:11 -07:00 |
|
|
Lianmin Zheng
|
f18d38d040
|
Revert "[AMD][Quantization] Online MXFP4 quantization 2/N - FP8 to MXFP4 requantization on AMD GPUs" (#28213)
|
2026-06-14 13:34:06 -07:00 |
|
|
Mick
|
3cb29f6747
|
[diffusion] feat: use regional torch.compile (compile_repeated_blocks) for DiT of diffusers backend (#28193)
|
2026-06-15 00:34:10 +08:00 |
|
|
Mick
|
ec36dde580
|
[diffusion] feat: add --warmup-mode enum server arg (#28184)
|
2026-06-14 23:09:04 +08:00 |
|
|
Mick
|
582bd23f71
|
[diffusion] feat: enable spatial-shard vae decode across GPUs (#28071)
|
2026-06-14 20:19:44 +08:00 |
|
|
|
d72314808f
|
[JIT Kernel] Multi-GPU test/bench framework for custom all-reduce + TP QKNorm (#26706)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: ziyi.xu <ziyi.xu@radixark.ai>
|
2026-06-14 17:20:36 +08:00 |
|
|
Mick
|
5331de0f8c
|
[diffusion] chore: resolve model_index.json Hub-first with local-cache fallback (#28177)
|
2026-06-14 16:48:38 +08:00 |
|
|
Humphrey
|
8c334e2224
|
fix(io_struct): index extra_key per sub-request in batched GenerateReqInput (#26971)
|
2026-06-14 00:50:38 -07:00 |
|
|
Mick
|
1456eb612d
|
[diffusion] CI: tighten perf baselines (#28123)
|
2026-06-14 15:50:21 +08:00 |
|
|
Jimmy Shongandgithub-actions[bot]
|
54acffc864
|
Eval accuracy gpqa aime25 mixins (#27102)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
|
2026-06-14 00:49:12 -07:00 |
|
|
Qiaolin Yu
|
f293ddf3ce
|
[perf] reduce overhead of fill_ids list reconstruction and decref (#27965)
|
2026-06-14 00:41:11 -07:00 |
|
|
Yongji Wu
|
f2d7d67603
|
numa: bind within allowed CPUs when affinity is already constrained (#26983)
|
2026-06-14 00:38:40 -07:00 |
|
|
|
b796338271
|
Fix prefill delayer wait histograms always observing 0 (#25975)
Co-authored-by: kingjameschan <170807154+kingjameschan@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Humphrey <181440142+humphreysun98@users.noreply.github.com>
|
2026-06-14 00:35:29 -07:00 |
|
|
David Wang
|
8c5320b37e
|
dflash add sliding window attention draft layer support (#27469)
|
2026-06-14 00:32:02 -07:00 |
|
|
Liangsheng Yin
|
bb48405c31
|
Unify NVTX annotation helpers and split the enable gate per subsystem (#28165)
|
2026-06-14 00:04:59 -07:00 |
|
|
ybyang
|
50993554d8
|
fix(health): make health-check rid unique across tokenizer workers (#28143)
|
2026-06-14 00:01:52 -07:00 |
|
|
|
f79a6b5c33
|
Support GLM-4.7 function calling via structural tags (#28149)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-06-14 14:57:07 +08:00 |
|
|
Mick
|
37ed10bd24
|
[diffusion] UX: reduce attention backend log noise (#28169)
|
2026-06-14 14:55:13 +08:00 |
|
|
Ting SUN
|
b250bea994
|
fix(sampling): reject non-finite temperature in SamplingParams.verify (#28153)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-06-13 23:41:36 -07:00 |
|
|
Yuzhen Zhou
|
171037c3e7
|
Fix Qwen3.5 deterministic batch-invariant logprobs (#27869)
|
2026-06-13 23:23:06 -07:00 |
|
|
Yanbin Jiang
|
1747b88c5e
|
[LoRA] Support DSA indexer LoRA targets for GLM-5.1 / DeepSeek-V3.2-family models (#28110)
|
2026-06-13 23:02:33 -07:00 |
|
|
Mick
|
31ac743484
|
[diffusion] chore: improve server warmup coverage (#28127)
|
2026-06-14 13:35:42 +08:00 |
|
|
Mohammad Miadh Angkad
|
91c63aeb4d
|
Fix stale CUDA graph benchmark and docs refs (#28041)
|
2026-06-13 21:51:42 -07:00 |
|
|
Jared Wen
|
5da3b37a9d
|
[CI] add Precision Regression Test on Nightly Run CI (#26902)
|
2026-06-14 12:43:57 +08:00 |
|
|
JoyFuture
|
a3fd5c24be
|
feat: add NVTX markers for the scheduler main loop (#27901)
|
2026-06-13 17:16:53 -07:00 |
|
|
Chang Min Bark
|
93b402580c
|
feat: add decode clear steps env var (#28160)
|
2026-06-13 17:15:42 -07:00 |
|
|
|
3f4a338212
|
[AMD][Quantization] Online MXFP4 quantization 2/N - FP8 to MXFP4 requantization on AMD GPUs (#18182)
Co-authored-by: Bowen Bao <bowenbao@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
|
2026-06-13 16:08:19 -07:00 |
|
|
billishyahao
|
10d3337048
|
[AMD] Support unified_kv_triton for disaggregation (#27935)
|
2026-06-13 14:08:27 -07:00 |
|
|
Oleg ZhelezniakandYorkSu
|
8a9f2aa116
|
fix: prevent stale bitmask leakage in LLGuidance grammar backend (#23653)
Signed-off-by: jellysnack <oleg.jellysnack@gmail.com>
Co-authored-by: YorkSu <45256779+YorkSu@users.noreply.github.com>
Co-authored-by: jellysnack <oleg.jellysnack@gmail.com>
|
2026-06-13 13:27:08 -07:00 |
|
|
Cheng Wan
|
27ba13358e
|
[Spec] Clear dead DRAFT_EXTEND objects left after EAGLE v1 removal (#28133)
|
2026-06-13 13:04:51 -07:00 |
|
|
Cheng Wan
|
bde6bccf39
|
[Spec] Remove deprecated EAGLE v1 DRAFT_EXTEND forward mode (#28129)
|
2026-06-13 13:00:21 -07:00 |
|
|
|
0e592395c7
|
[Apple Silicon] [MLX] Fuse SwiGLU activation into gate gather_qmv for SwitchGLU MoE blocks (#26188)
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: R0CKSTAR <yeahdongcn@gmail.com>
|
2026-06-13 21:57:57 +08:00 |
|
|
Yuhao Yang
|
aea0e30853
|
[4/N] Qwen3.5Opt: Overlap mamba verify update with draft extend (#26924)
|
2026-06-13 20:29:20 +08:00 |
|
|
McZyWu
|
f7041c9dee
|
step3.5 flash revise for graph mode and use triton activation (#27739)
|
2026-06-13 16:34:20 +08:00 |
|
|
|
806365e778
|
feat: Support HiCache for MiMo-V2 models (1/N) (#27378)
Co-authored-by: Zhangheng <hzh0425@apache.org>
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
|
2026-06-13 15:40:27 +08:00 |
|
|
billishyahao
|
60d4bd4c70
|
[AMD] fix moriep quant kernel not implemented issue (#27855)
|
2026-06-13 00:35:41 -07:00 |
|
|
Yongji Wu
|
568aa5fcdb
|
Fix missing draft KV pool transfers in HybridCacheController (#27953)
|
2026-06-13 15:17:31 +08:00 |
|
|
Zhangheng
|
8ce05e8a20
|
[UnifiedTree]: Pin host buffers across async H→D in UnifiedRadixCache.load_back (#27444)
|
2026-06-13 15:16:56 +08:00 |
|
|
inkcherryandDuyi-Wang
|
eb9483b5c2
|
[PD][AMD]: incremental KV transfer with decode radix cache (#26288)
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
Co-authored-by: Duyi-Wang <duyi.wang@amd.com>
|
2026-06-13 00:06:44 -07:00 |
|
|
shuwenn
|
f4029d0fc0
|
[HiCache] fix: clear storage reset state (#26009)
|
2026-06-12 23:51:26 -07:00 |
|
|
Mick
|
cb4933b22e
|
[diffusion] optimize: enable vae parallel decode with cfg-parallel (#27875)
|
2026-06-13 13:52:27 +08:00 |
|
|
Mick
|
8becb37519
|
[diffusion] warmup: improve diffusion server warmup (#28119)
|
2026-06-13 13:04:10 +08:00 |
|