Skip to content

Pull requests: intel/llm-scaler

New pull request New
28 Open 351 Closed
28 Open 351 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

docker: upgrade production vLLM image to 0.26.0
#655 opened Aug 31, 2026 by gc-fu Contributor Loading…
vLLM: integrate FP16 packed QSA extension
#651 opened Aug 28, 2026 by xiangyuT Contributor Loading…
qwen38 kernels
#650 opened Aug 28, 2026 by hzjane Contributor • Draft
[vLLM][XPU] 修复 torch.compile 跟踪时 LoRA 算子被裁剪的问题
#635 opened Aug 20, 2026 by sicnuyudidi Loading…
1
omni: INT4 per-block zero-point GEMM + calling adapter (torchao asymmetric INT4)
#629 opened Aug 19, 2026 by JWLHS Loading…
5
docs(vllm): Qwen3.8-27B DFlash drafter recipe — 72.2 tok/s on Arc Pro B70
#620 opened Aug 16, 2026 by rmacy Loading…
3
docker: upgrade dev vLLM image to 0.26.0
#604 opened Aug 7, 2026 by gc-fu Contributor • Draft
3
docs(omni): add HiDream-O1, Krea2 Turbo, Boogu-Image, Mage-Flow and LTX-2.3 to supported models table
#592 opened Aug 4, 2026 by KristianZeng Contributor Loading…
1
delete comfyui-mixlab-node
#581 opened Jul 31, 2026 by zhm-algo Contributor Loading…
[XPU] Harden fused GDN recurrent state updates
#570 opened Jul 27, 2026 by gc-fu Contributor Loading…
Fix #533: guard out_proj.weight access in GDN out-projection ESIMD probes
#557 opened Jul 22, 2026 by joaovgaraujo Loading…
1
refactor(omni): multi-stage Docker build with decoupled builder/runtime
#549 opened Jul 17, 2026 by KristianZeng Contributor • Draft
1
SGL: Add Gemma4 31b support
#542 opened Jul 15, 2026 by xiangyuT Contributor • Draft
fix(esimd): declare INT4 output mutations
#537 opened Jul 13, 2026 by gc-fu Contributor Loading…
page_attn: make global-max reduction order-invariant
#535 opened Jul 12, 2026 by taste-software Loading…
1
Fix/gdn conv seq fp32 state
#500 opened Jun 29, 2026 by liu-shaojun Contributor • Draft
Feat/gemma4 int4 group32
#499 opened Jun 29, 2026 by hzjane Contributor • Draft
Fix Qwen3.5/3.6 load_weights stacked-mapping name mutation (gate_gate_up_proj / qkqkv_proj)
#475 opened Jun 12, 2026 by bongmiin Loading…
vllm: add MiniCPM-V 4.6 support (MiniCPMV4_6ForConditionalGeneration)
#472 opened Jun 12, 2026 by Zjq9409 Loading…
1
Optimize gemma4 continue
#470 opened Jun 11, 2026 by hzjane Contributor • Draft
Feature/prefill fmha esimd
#425 opened May 21, 2026 by liu-shaojun Contributor • Draft
esimd: fix resadd_norm_gemv_int4 race on large N
#399 opened May 10, 2026 by hzjane Contributor • Draft
Add Lunar Lake Xe2 iGPU compatibility report and benchmarks
#342 opened Apr 1, 2026 by MegaStood Loading…
fix: VLLM_SKIP_PROFILE_RUN patch for Lunar Lake iGPU profile_run() hang
#340 opened Apr 1, 2026 by MegaStood Loading…
1
docs: GLM-4.7-Flash MLA bug analysis, patches, and MoE investigation for Lunar Lake XPU
#334 opened Mar 25, 2026 by MegaStood Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.