sglang

awq

[GPTQ] Refactor CPU quantization schemes (#26786 )

2026-06-08 13:14:40 +03:00

compressed_tensors

[GPTQ] Refactor CPU quantization schemes (#26786 )

2026-06-08 13:14:40 +03:00

configs

Fix result writer in tuning_block_wise_kernel.py, and add FP8 kernel config for L40 (#20368 )

2026-03-20 09:28:54 +08:00

gptq

[GPTQ] Refactor CPU quantization schemes (#26786 )

2026-06-08 13:14:40 +03:00

modelslim

[Fix][NPU] Preserve existing packed_modules_mapping when merging model-level fused module mappings (#25755 )

2026-05-29 09:11:36 +08:00

quark

[AMD] Enable Piecewise CUDA Graph for AMD GPUs (#22299 )

2026-06-07 16:28:20 -07:00

__init__.py

[GPTQ] Refactor CPU quantization schemes (#26786 )

2026-06-08 13:14:40 +03:00

auto_round.py

[GPTQ] Refactor CPU quantization schemes (#26786 )

2026-06-08 13:14:40 +03:00

base_config.py

[Fix][NPU] Preserve existing packed_modules_mapping when merging model-level fused module mappings (#25755 )

2026-05-29 09:11:36 +08:00

base_scheme.py

[2/N] Quantization Refactor: Compressed tensors MoE schemes (#17503 )

2026-02-16 18:03:51 +03:00

bitsandbytes.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

blockwise_int8.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

fp4_kv_cache_quant_method.py

[1/4] NVFP4 KV cache: quantization strategy abstraction and kernel (#21954 )

2026-04-29 01:45:48 -07:00

fp4_utils.py

Changes for SM120 perf and usability for NVFP4 (#26496 )

2026-06-04 15:29:25 -07:00

fp8_kernel.py

[Gemma4]: Fix FP8 Triton scale layout (#25286 )

2026-05-19 14:00:23 -07:00

fp8_utils.py

[NVIDIA] Fix FP8 gemm performance with fp16 models (MInimax-M2.5) (#22300 )

2026-06-07 02:45:00 +00:00

fp8.py

[NVIDIA] Fix FP8 gemm performance with fp16 models (MInimax-M2.5) (#22300 )

2026-06-07 02:45:00 +00:00

fpgemm_fp8.py

[lint] improve ruff check (#11922 )

2025-10-22 11:32:50 +08:00

gguf.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

int8_kernel.py

chore: fix some typos (#18577 )

2026-02-10 20:47:41 -08:00

int8_utils.py

…

kv_cache.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

kvfp4_tensor.py

[1/4] NVFP4 KV cache: quantization strategy abstraction and kernel (#21954 )

2026-04-29 01:45:48 -07:00

marlin_utils_fp4.py

Feat/add w4a16 moe support to nemotron (#25655 )

2026-06-02 22:42:26 -07:00

marlin_utils_fp8.py

[misc] clean up kernel API (#21325 )

2026-03-25 09:10:23 +08:00

marlin_utils.py

Feat/add w4a16 moe support to nemotron (#25655 )

2026-06-02 22:42:26 -07:00

mlx.py

[Apple Silicon] [MLX] Auto-detect MLX-format quantization_config dict (#25191 )

2026-05-14 09:55:37 -07:00

modelopt_quant.py

Nemotron perf changes (#26733 )

2026-06-05 22:31:46 -07:00

moe_wna16.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

mxfp4_flashinfer_cutlass_moe.py

[MoE Refactor] Migrate SM90 Cutlass W4A16 to MoeRunner (#26489 )

2026-05-30 02:02:56 -07:00

mxfp4_flashinfer_trtllm_moe.py

Use Cute-DSL MXFP8 quantize kernels (#25486 )

2026-05-28 00:01:31 -07:00

mxfp4_marlin_moe.py

feat: SM120 (Blackwell Desktop) support for DeepSeek-V4 inference (#24692 )

2026-06-01 14:05:20 -07:00

mxfp4_tensor.py

[sgl-kernel] misc: update deepgemm version for sgl-kernel (#9340 )

2025-08-27 12:01:30 -07:00

mxfp4.py

[AMD] Optimize gpt-oss-120B performance (#27063 )

2026-06-07 20:06:30 -07:00

nvfp4_gemm_swiglu_nvfp4_quant.py

[perf] Fuse NVFP4 gate_up_gemm + swiglu + output FP4 quant (#26626 )

2026-05-29 13:16:24 -07:00

petit_utils.py

Revert "feat: Support MXFP4 quantized dense models on AMD CDNA2/CDNA3 GPUs (#19143 )" (#23031 )

2026-04-16 21:53:25 -07:00

petit.py

chore: add vLLM SPDX copyright headers to ported files (#25182 )

2026-05-13 15:17:30 -07:00

qoq.py

Refactor: move all quantization-related code to srt/layer/quantization (#7989 )

2025-07-17 00:47:07 -07:00

quark_int4fp8_moe.py

[MoE] Unify DeepEPMoE+MoriEPMoE through AITER MoeRunner pre/post-permute (#23760 )

2026-05-17 02:25:52 -07:00

rocm_mxfp4_utils.py

Optimized deepseek-v3/r1 model performance on mxfp4 run (#10008 )

2025-09-04 15:11:22 -07:00

unquant.py

Nemotron perf changes (#26733 )

2026-06-05 22:31:46 -07:00

utils.py

[loader] Reduce transient allocations in NVFP4 MoE setup (#26861 )

2026-06-03 21:13:25 -07:00

w4afp8.py

[Reland] DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication (#22316 )

2026-04-10 14:56:05 +08:00

w8a8_fp8.py

[Lora] Lora quat info re-factor and support deepseekv3 mla lora (#22323 )

2026-04-09 14:19:58 -07:00

w8a8_int8.py

[CPU] Add GPT-OSS model optimization for CPU (#16775 )

2026-05-29 16:05:26 +08:00