Commit Graph
26 Commits
Author SHA1 Message Date
Ming YangandMichael Goin 6831650c40 [offloader] v2: Hide weight onloading latency via prefetching (#29941)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2026-02-25 17:20:59 -08:00
Ming Yang 3bb9561928 Revert "[bench] Support common prefix len config (for decode-only bench)" (#31240)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-23 21:17:23 -08:00
Ming Yang 8372be2828 [moe] Use enable_chunking func (to support disabling chunking) (#29935)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-18 09:02:38 +00:00
Ming Yang ce12b407f2 [TRTLLM] Remove the MoE GEMM weight name change (#30713)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-16 11:01:38 -05:00
Ming Yang fba8906930 [perf] Use direct copy (broadcast) instead of cat for k_nope/k_pe in MLA prefill (#29710)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-11 08:20:45 +00:00
Ming Yang 9d6235ca9a [moe] Allow disabling DP chunking (#29936)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-09 00:29:36 +00:00
Ming Yang 60d17251c9 [Disagg] Support large batch size in proxy server and update NixlConnector doc for DP (#28782)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-09 00:01:08 +00:00
Ming Yang f16356fe36 [bench] Support common prefix len config (for decode-only bench) (#29934)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-05 10:26:52 +00:00
Ming Yang 0f67d4d962 [Attention] Add MLA prefill backend: trtllm_ragged_attention_deepseek (#26397)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-10-24 10:24:08 -07:00
Ming Yang 3b736e1c38 [Attention][DCP] Support DCP with query length > 1 (MTP) with FA3 (#25049)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-10-09 08:06:29 -07:00
Ming Yang 4e5affeaa1 [CI] Add Decode Context Parallelism (DCP) test to CI (#24487)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-09-16 21:21:28 +08:00
Ming Yang 4032949630 [Bugfix] Fix DeepEP config for DP4TP4 (#23619)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-09-10 10:37:56 -07:00
Ming Yang 1823a00d67 [Misc] Support bench serve long context (#24373)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-09-08 22:53:10 -07:00
Ming Yangandyoukaichao 86173ad593 [Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA (#24385)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-09-08 09:27:12 +08:00
Ming Yang 504d914314 [Perf] Add Triton config for DeepSeek V3 FP8 EP32 H200 (#23504)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-08-24 18:06:35 -07:00
Ming Yang 10f535c086 [Bugfix] Fix port conflict by obtaining a list of open ports upfront (#21894)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-08-21 10:22:18 -07:00
Ming YangTyler Michael Smithgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
82216dc21f [Misc] Support routing logic simulation (#21990)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-06 23:06:20 -07:00
Ming Yang f12d9256b3 [Misc] Use dracut on CentOS and skip clone if repo exists for EP kernel installation (#21635)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-07-30 13:15:06 -07:00
Ming Yang 2ded067fd2 [Bugfix] Fix CUDA arch flags for MoE permute (#21426)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-07-24 03:23:59 -07:00
Ming YangandCyrus Leung 772ce5af97 [Misc] Add dummy maverick test to CI (#21324)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-07-23 20:22:42 -07:00
Ming Yang e7b2042681 Revert "[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) (#21334)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-07-21 21:49:01 -07:00
Ming Yangandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 6ece16c4fe [Misc] Add dummy maverick test (#21199)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-07-21 09:08:09 -07:00
Ming Yang fcb9f879c1 [Bugfix] Correct per_act_token in CompressedTensorsW8A8Fp8MoECutlassM… (#20937)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-07-15 19:53:42 -07:00
Ming Yang 3de2ed767f [Bugfix] Remove assertion of expert_map being None (#20714)
Signed-off-by: Ming Yang <yming@meta.com>
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-07-10 19:55:22 +00:00
Ming Yang c438183e99 [Bugfix] Fix topk_ids indices_type for CUTLASS w8a8 FP8 MoE (#20166)
Signed-off-by: Ming Yang <yming@meta.com>
2025-07-08 23:10:57 +00:00
Ming Yang afb7cff1b9 [Bugfix] Fix Maverick correctness by filling zero to cache space in cutlass_moe (#20167)
Signed-off-by: Ming Yang <yming@meta.com>
2025-07-08 01:07:22 +00:00