Files

T

a952e9174f [MLX] Support Qwen3.5 (dense) Model (#25754 )

Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

2026-05-30 17:05:02 +08:00

benchmark

bench_serving: add Zipfian shared-prefix sampling to generated-shared-prefix (#26378 )

2026-05-28 14:39:46 -07:00

cli

Support --model as alias for --model-path in CLI (#23894 )

2026-04-28 17:23:27 -07:00

eval

Fix none-comparison (E711) warnings (#19745 )

2026-03-06 16:15:21 -08:00

jit_kernel

[diffusion][jit_kernel] perf: varlen FA fast path for USPAttention masked branch (#26318 )

2026-05-28 21:26:09 +08:00

lang

[Lint] Fix Optional[X] = (None,) typo defaults in two dataclasses (#25252 )

2026-05-15 00:32:40 -07:00

multimodal_gen

[Fix] Fix FP8 Online Quantization (#26415 )

2026-05-28 22:00:09 -07:00

srt

[MLX] Support Qwen3.5 (dense) Model (#25754 )

2026-05-30 17:05:02 +08:00

test

[CI] ci-coverage-overview: schedule + manual only, include XPU/MUSA/multimodal_gen (#26619 )

2026-05-30 16:39:18 +08:00

__init__.py

feat: add Crusoe managed inference backend (#20475 )

2026-05-12 16:23:23 -07:00

_mps_stub.py

[MPS] Add StreamContext stub (#20782 )

2026-03-25 20:59:51 -07:00

_triton_stub.py

[MPS] Fix Triton stub sub-module imports on Python 3.12+ (#21551 )

2026-03-31 20:26:01 -07:00

auto_benchmark_lib.py

[Benchmark] Add auto benchmark tool with YAML-driven server flag search and canonical dataset format (#21736 )

2026-04-04 21:46:58 +08:00

auto_benchmark.py

[Benchmark] Add auto benchmark tool with YAML-driven server flag search and canonical dataset format (#21736 )

2026-04-04 21:46:58 +08:00

bench_offline_throughput.py

Add Ray actor support for scheduler process management (DP=1) (#17684 )

2026-03-05 13:21:23 -08:00

bench_one_batch_server.py

bench: fix wrong flag names in bench_one_batch{,_server} docstrings (#25143 )

2026-05-12 23:46:47 -07:00

bench_one_batch.py

[MLX] Support Qwen3.5 (dense) Model (#25754 )

2026-05-30 17:05:02 +08:00

bench_serving.py

bench_serving: add Zipfian shared-prefix sampling to generated-shared-prefix (#26378 )

2026-05-28 14:39:46 -07:00

check_env.py

[Bugfix] [NPU] Fix check_env on Ascend for CANN 8.5 (#22888 )

2026-04-17 04:05:20 +03:00

compile_deep_gemm.py

[Bugfix] Fix DeepEP timeout when compiling DeepGeMM in EP+DP+TP (#23185 )

2026-04-19 17:36:11 -07:00

global_config.py

…

kernel_api_logging.py

[misc] clean up kernel API (#21325 )

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

launch_server.py

[gRPC] Native gRPC server: proto + Rust crate scaffold + server args (#22736 )

2026-04-20 12:39:35 +08:00

profiler.py

Migrate all callers from /get_server_info to /server_info (#21463 )

2026-04-01 21:17:50 -07:00

README.md

…

utils.py

[diffusion] feat: add performance mode server args (#24491 )

2026-05-14 00:57:46 +08:00

version.py

…

README.md

Code Structure

eval: The evaluation utilities.
lang: The frontend language.
multimodal_gen: Inference framework for accelerated image/video generation.
srt: The backend engine for running local models. (SRT = SGLang Runtime).
test: The test utilities.
api.py: The public APIs.
bench_offline_throughput.py: Benchmark the performance in the offline mode.
bench_one_batch.py: Benchmark the latency of running a single static batch without a server.
bench_one_batch_server.py: Benchmark the latency of running a single batch with a server.
bench_serving.py: Benchmark online serving with dynamic requests.
check_env.py: Check the environment variables and dependencies.
global_config.py: The global configs and constants.
launch_server.py: The entry point for launching a local server.
profiler.py: The profiling entry point to send profile requests.
utils.py: Common utilities.
version.py: Version info.