popov/neuron-tai
1
0
Fork 0
Code Issues 42 Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'archived_ralph/dgr-001-performance-contract' into merge/all-branches-into-master

Browse Source 
# Conflicts:
#	.claude/memory/MEMORY.md
#	.scratch/distributed-gguf-runtime/PRD.md
#	.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md
#	.scratch/distributed-gguf-runtime/README.md
#	.scratch/distributed-gguf-runtime/architecture.md
#	.scratch/distributed-gguf-runtime/evidence/DGR-017/README.md
#	.scratch/distributed-gguf-runtime/implementation-strategy.md
#	.scratch/distributed-gguf-runtime/issues/07-add-isolated-concurrent-local-hot-kv-state.md
#	.scratch/distributed-gguf-runtime/issues/13-harden-failure-cancellation-and-restart-semantics.md
#	.scratch/distributed-gguf-runtime/milestones.md
#	.scratch/distributed-gguf-runtime/prd.json
#	docs/issues/distributed-gguf-runtime/01-lock-the-safetensors-versus-gguf-performance-contract.md
#	docs/issues/distributed-gguf-runtime/02-adopt-the-versioned-grpc-shard-protocol.md
#	docs/issues/distributed-gguf-runtime/03-define-exact-artifact-and-runtime-recipe-identity.md
#	docs/issues/distributed-gguf-runtime/05-implement-dense-llama-range-aware-gguf-ownership.md
#	docs/issues/distributed-gguf-runtime/06-implement-architecture-defined-boundary-input-output.md
This commit is contained in:
Dobromir Popov
2026-07-17 13:44:52 +03:00
parent 9cb334cced 1749f9b4ad
commit f0ddb69d33
124 changed files with 24939 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
packages/node/meshnet_node/torch_server.py
View File

@@ -19,7 +19,6 @@ from .model_backend import (
InsufficientVRAMError,
KVCacheMiss,
MissingModelDependencyError,
Quantization,
TailTokenResult,
TorchModelShard,
_tensor_from_bfloat16_bytes,
@@ -46,7 +45,7 @@ class _DirectRequestUncertainError(ConnectionError):
"""A direct request may have reached the downstream node but did not finish."""
from .server import (
from .server import ( # noqa: E402
_WIRE_VERSION,
_parse_shape,
_validate_activation_body,
@@ -399,7 +398,7 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
# Finite responses below provide Content-Length; streams are chunked.
protocol_version = "HTTP/1.1"
def log_message(self, fmt, *args): # noqa: suppress request logs in tests
def log_message(self, fmt, *args): # suppress request logs in tests
pass
def _request_id(self) -> str: