GitLab

修复CompressedTensorsLinearMethod中的w4a16的冲突问题
feat(moe): add Marlin W16A16 fused MoE behind VLLM_USE_MARLIN_W16A16_MOE
replace the fp8_mqa_logits and fp8_paged_mqa_logits interfaces in deepgemm with mqa_logits and paged_mqa_logits from lightop

去掉无效代码

See merge request dcutoolkit/deeplearing/vllm!285

This reverts commit 3b121add.

Add new benchmark configurations for gfx936_80cu with E=512,N=64 and E=512,N=128 Qwen3-Next-80B-A3B-Instruct nn tp4 tp8 moe json

See merge request dcutoolkit/deeplearing/vllm!283

Add new benchmark configurations for gfx936_80cu with E=512,N=64 and E=512,N=128 Qwen3-Next-80B-A3B-Instruct nn tp4 tp8 moe json

add VLLM_USE_OPT_RESHAPE_AND_CACHE、VLLM_USE_FUSE_SILU_AND_MUL and VLLM_USE_TOPK_RENORM for qwen3-30b

Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
(cherry picked from commit d7284a26)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
(cherry picked from commit 5cdd6645)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
(cherry picked from commit 0ec84221)

Signed-off-by: juliendenize <julien.denize@mistral.ai>
(cherry picked from commit 1b1e35aa)

Signed-off-by: juliendenize <julien.denize@mistral.ai>
(cherry picked from commit 5e5646e2)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
(cherry picked from commit 0a9caca9)

Signed-off-by: Sage Moore <sage@neuralmagic.com>
(cherry picked from commit e6f114ac)

Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
(cherry picked from commit 1528e079)

Signed-off-by: bbartels <benjamin@bartels.dev>
(cherry picked from commit 2d613de9)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
(cherry picked from commit 51c57b51)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
(cherry picked from commit 68ffbca7)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 951445a5)

Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Mickael Seznec <mickael@mistral.ai>

Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Li, Jiang <bigpyj64@gmail.com>

Signed-off-by: Boyuan Feng <boyuan@meta.com>

Signed-off-by: zhyajie <yajizhan@amd.com>
Co-authored-by: zhyajie <yajizhan@amd.com>

Signed-off-by: Boyuan Feng <boyuan@meta.com>

Signed-off-by: Wushi Dong <dongws@meta.com>