Eric ZhangandClaude Opus 5 f3ed82b3a8 [inkling] Let Anthropic thinking=disabled map to reasoning effort "none" (#33913) ...

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-08-08 21:59:32 +08:00

..

arg_groups

moe: the shared-experts-fusion decision is a per-runner value the loader installs (#33889)

2026-08-07 22:42:58 -07:00

batch_invariant_ops

[NPU]adaptation to support deterministic inference (#21197)

2026-06-09 09:22:09 +08:00

batch_overlap

config: retire the last process-global config field reads (#33338)

2026-08-02 21:24:42 -07:00

checkpoint_engine

…

compilation

[Kernel] Unify BaseFusedOp and MultiPlatformOp dispatch (#33205)

2026-08-06 08:52:09 +08:00

configs

Add registered short-conv tests and backend extensions (#34045)

2026-08-08 14:38:03 +08:00

connector

[connector] Add Azure Blob Storage connector (az:// and *.blob.core.windows.net URLs) (#23995)

2026-05-11 14:20:22 -07:00

constrained

[Fix] Treat an empty grammar constraint as unset in SamplingParams (#33328)

2026-08-02 21:45:51 -07:00

debug_utils

config: read resolved config via namespace accessors (#33013)

2026-07-31 15:06:59 -07:00

disaggregation

config: retire ServerArgs.derive; per-runner values are constructor arguments (#33887)

2026-08-07 22:41:09 -07:00

distributed

[Distributed] Propagate semantic group names to PyTorch process groups (#32900)

2026-08-06 20:38:12 -07:00

dllm

config: read resolved config via namespace accessors (#33013)

2026-07-31 15:06:59 -07:00

elastic_ep

[Mooncake] Fix ProcessGroup API imports (#32403)

2026-08-03 01:16:41 -07:00

entrypoints

[inkling] Let Anthropic thinking=disabled map to reasoning effort "none" (#33913)

2026-08-08 21:59:32 +08:00

eplb

config: route parallel config-leaf reads through get_parallel() (#33170)

2026-08-01 08:58:39 -07:00

function_call

[Kimi K3] Add reasoning, tool-call, and OpenAI serving support (#33025)

2026-08-01 14:57:23 -07:00

grpc

…

hardware_backend

[Bugfix] Fix batched KV free aliasing (#34067)

2026-08-08 03:34:44 -07:00

kv_canary

Radix Cache Split: Spin off TreeCore (#29901)

2026-07-25 14:31:59 -07:00

layers

[Scheduler] Unify WAR read-done gating behind shared-read boundary declarations (#34052)

2026-08-08 03:26:36 -07:00

lora

Support Intern-S2-Mobius (#33691)

2026-08-08 11:06:57 +08:00

managers

feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936)

2026-08-08 16:00:58 +08:00

mem_cache

[Bugfix] Fix batched KV free aliasing (#34067)

2026-08-08 03:34:44 -07:00

model_executor

fix: always capture default prefill CUDA graph (#33352)

2026-08-08 19:24:49 +08:00

model_loader

feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936)

2026-08-08 16:00:58 +08:00

models

feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936)

2026-08-08 16:00:58 +08:00

multimodal

feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936)

2026-08-08 16:00:58 +08:00

multiplex

config: read resolved config via namespace accessors (#33013)

2026-07-31 15:06:59 -07:00

observability

Observability enhancement for HiCache (#32388)

2026-08-05 14:13:06 -07:00

parser

[inkling] Render tool-result media instead of coercing content to str (#33898)

2026-08-08 14:39:19 +08:00

platforms

[Kernel] Unify BaseFusedOp and MultiPlatformOp dispatch (#33205)

2026-08-06 08:52:09 +08:00

plugins

…

ray

config: pass the Ray placement group as a launch argument

2026-08-05 19:28:39 -07:00

sampling

config: delete the dead get_server_args() bindings across the repo (#33888)

2026-08-07 22:41:53 -07:00

session

feat: Session-reference-aware Unified Radix Cache for agentic multi-turn workloads (#29173)

2026-08-02 13:43:55 +08:00

speculative

[Scheduler] Unify WAR read-done gating behind shared-read boundary declarations (#34052)

2026-08-08 03:26:36 -07:00

state_capturer

moe: the shared-experts-fusion decision is a per-runner value the loader installs (#33889)

2026-08-07 22:42:58 -07:00

tokenizer

Add Inkling model support (#31681)

2026-07-19 22:57:37 -07:00

utils

Support Intern-S2-Mobius (#33691)

2026-08-08 11:06:57 +08:00

weight_cache

config: route parallel config-leaf reads through get_parallel() (#33170)

2026-08-01 08:58:39 -07:00

weight_sync

Introduce WeightUpdater and WeightExporter components (#31148)

2026-07-14 15:53:33 +08:00

constants.py

[AMD][MXFP4] Online MXFP4 quantization 1/N - dense and MOE models w. original BF16 weight (#18005)

2026-06-03 12:55:24 -07:00

environ.py

Reland serving-time Triton load diagnostics (#33908)

2026-08-07 14:51:43 -07:00

runtime_context.py

moe: the shared-experts-fusion decision is a per-runner value the loader installs (#33889)

2026-08-07 22:42:58 -07:00

server_args_config_parser.py

fix(server): serialize nested dict config values as JSON (#28094)

2026-06-12 19:27:31 -07:00

server_args.py

feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936)

2026-08-08 16:00:58 +08:00