 Minglei Zhu
|
4bffd3a232
|
[GPT-OSS] support fp8 online quantization for gpt-oss bf16 (#18988)
merge it as all required CI passed
|
2026-02-20 14:16:57 -08:00 |
|
|
Minglei Zhu
|
bf52388354
|
[PCG] support piecewise cuda graph for kimi-linear model (#18849)
|
2026-02-17 23:31:12 +08:00 |
|
|
Minglei Zhu
|
8be18c655d
|
[Perf] refactor piecewise cuda graph support of Qwen3-Next (#17613)
|
2026-02-14 09:30:50 +08:00 |
|
|
Minglei Zhu
|
38d275a9fd
|
[BugFix] fix gpt-oss accuracy issue when enabling piecewise cuda graph (#18013)
|
2026-02-01 14:26:26 +08:00 |
|
|
Minglei Zhu
|
d90c0837e5
|
[hybrid-model] clean up and consolidate redundant fields in RadixLinearAttention (#17660)
|
2026-01-27 10:37:58 -08:00 |
|
|
Minglei Zhu
|
2b2f317383
|
fix gpt-oss launch failure with piecewise cuda graph (#17532)
|
2026-01-22 22:41:38 -08:00 |
|
|
Minglei Zhu
|
419bbcee10
|
refactor Qwen3-Next with a new RadixLinearAttention (#17373)
|
2026-01-22 17:42:06 +08:00 |
|
|
Minglei ZhuandMinglei Zhu
|
64946679b5
|
[Perf] fuse q, k norm for Flux2Attention (#17241)
Co-authored-by: Minglei Zhu <zminglei@linkedin.com>
|
2026-01-19 14:33:34 +08:00 |
|
|
Minglei Zhu
|
a2c2c09d7d
|
[BugFix] fix gpt-oss-120b launch failure with --enable-piecewise-cuda-graph (#16757)
|
2026-01-11 09:19:59 +08:00 |
|
|
Minglei Zhu
|
4c85f9d039
|
Only allocate encoder metadata for encoder-decoder models (#16527)
|
2026-01-06 22:17:04 -08:00 |
|
|
Minglei ZhuandBinyao Jiang
|
b62e7e3bfe
|
[CI]add nightly CI for glm4v_moe arch model (#14927)
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
|
2025-12-11 18:29:45 -08:00 |
|
|
Minglei Zhu
|
be4a3ec376
|
support piecewise cuda graph for Olmo models (#14476)
|
2025-12-06 17:57:44 -08:00 |
|
|
Minglei Zhu
|
b76e303e6a
|
clean up gemlite usage (#14444)
|
2025-12-04 21:52:56 -08:00 |
|
|
|
e8542db558
|
[piecewise] move piecewise_cuda_graph_runner init to model_runner initialize (#14034)
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
|
2025-11-30 22:16:04 -08:00 |
|
|
Minglei Zhu
|
fafaa2ccea
|
[BugFix] fix outplace_fused_experts missing is_gated (#13864)
|
2025-11-24 12:36:14 -08:00 |
|
|
Minglei Zhu
|
3798055929
|
purge unnecessary env variable set in deterministic test (#13481)
|
2025-11-18 20:43:51 -08:00 |
|
|
Minglei Zhu
|
9846f8ed72
|
fix MambaPool clear method after refactoring (#13449)
|
2025-11-18 10:03:45 +08:00 |
|
|
Minglei Zhu
|
8a4373405e
|
re-submit 12911 but relax the requirement for deepgemm (#13226)
|
2025-11-15 15:37:12 +08:00 |
|
|
Minglei Zhu
|
a5be6ef98e
|
[Deterministic] Support Qwen3-Next model deterministic inference (#13100)
|
2025-11-14 18:01:18 -08:00 |
|
|
Minglei Zhu
|
8a821af793
|
fallback to triton mm_persistent kernel when deepGemm fail (#12911)
|
2025-11-08 23:42:26 -08:00 |
|
|
Minglei Zhu
|
c14cc47e39
|
[Deterministic] Optimize bmm_batch_invariant op (#12522)
|
2025-11-04 00:33:31 -08:00 |
|
|
Minglei Zhu
|
229256c505
|
[Deterministic] add deepseek v3 deterministic inference CI test (#12412)
|
2025-11-01 18:10:32 -07:00 |
|
|
Minglei Zhu
|
e39628fd07
|
[2/2] Deepseek deterministic: support deepseek v3 deterministic inference on 8 x H200 (#12095)
|
2025-10-29 11:49:04 -07:00 |
|
|
Minglei Zhu
|
f4b78d137c
|
[1/2] deepseek deterministic: support deterministic inference for deepseek arch models on a single GPU (#12000)
|
2025-10-24 15:17:28 -07:00 |
|
|
Minglei Zhu
|
200a3c0bb1
|
[Documentation] add doc for deterministic inference (#11956)
|
2025-10-22 12:36:15 -05:00 |
|
|
Minglei Zhu
|
f4488e9dd9
|
set default attention backend for deterministic inference (#11801)
|
2025-10-18 00:01:24 -07:00 |
|
|
Minglei ZhuandBaizhou Zhang
|
13219e1e48
|
completely remove mixed mode deterministic test as prefix mode could cover it (#11783)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2025-10-17 17:46:03 -07:00 |
|
|
Minglei Zhu
|
46ccbed2cd
|
update GLM nightly test threshold (#10331)
|
2025-09-11 14:54:58 -07:00 |
|
|
Minglei Zhu
|
6ee6619b7a
|
add zai-org/GLM-4.5-Air-FP8 model into nightly CI (#8894)
|
2025-08-08 01:44:19 -07:00 |
|
|
|
2ae95d17e8
|
Disable tp for shared experts under expert parallelism for GLM4.5 model (#8647) (#8647)
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
|
2025-08-01 12:02:35 -07:00 |
|
|
Minglei Zhu
|
25f73c6cf3
|
fix GLM4_MOE launch with compressed_tensor quant model (#8456)
|
2025-07-28 01:31:20 -07:00 |
|
|
Minglei Zhu
|
8a32355704
|
Feat: Support Granite 3.0 MoE in SGLang (#7959)
|
2025-07-17 20:56:03 -07:00 |
|
|
Minglei Zhu
|
79961afa82
|
optimize pad operations in fa3 to accelarate 100+us (#6077)
|
2025-05-07 23:40:08 -07:00 |
|