Serve chat without forced thinking

Test think prefill with pinned SFT epoch 3 revision

Document 1024-token generation default

Fix Unicode characters in streamed responses

Compact chat context at 1024 tokens

Document 512-token generation default

Deploy PIQA-selected full-SFT epoch 2 root model

Download only refinement inference files

Deploy MoE architecture metadata fix

Serve the 160B refinement model as raw completion

Stop forcing Thinking from the model chat template

Name the Space card explicitly as TR-HASH MoE

Force the bundled Thinking chat template at runtime

Force the bundled Thinking chat template at runtime

Deploy TR-HASH MoE 200M 160B-token Thinking LoRA

Serve intermediate TR-HASH-200M-70B-SFT checkpoint

Rename Space display to TR-Hash Tiny

Serve AETHORIA TR-HASH-200M-130B

Bump TR-Hash-i64 to 8dd8256

Bump TR-Hash-i64 pin to the multi-hash routing loader fix

Bump tr_hash_i64 pin to 9f9766b (MPSGraphRunner, INL - 2025 cleanup)

Bump tr_hash_i64 pin to 8b9d77a (checkpoint path resolution fix)

Bump tr_hash_i64 pin to f79196f (MPS support, 200M registry entry)

Bump tr_hash_i64 pin to 8040970 (decode_step CUDA graph fix, hash-routing audit)

Sync with the renamed TR-Hash-i64 server (was vllm-i64): repo URL, module import, env var names

Sync with the renamed TR-Hash-i64 server (was vllm-i64): repo URL, module import, env var names

Sync with the renamed TR-Hash-i64 server (was vllm-i64): repo URL, module import, env var names

Reload optional-thinking chat template

Rebuild with bounded thinking finalization

Rebuild with vllm-i64 a44a472

Deploy reasoning-history context isolation

Isolate chat prefix cache by conversation

Isolate prefix cache by conversation

Do not charge telemetry against chat rate limit

Document internal model identifier

Fix TR-Hash Space model identifier

Rename public demo to TR-HASH-0.5B

Apply embedded Hugging Face chat template

Mount TR-Hash 500M model volume

Serve TR-Hash MoE 500M

Rebuild with vllm-i64 71e005a

Add live top-2 expert telemetry e787df1

Rebuild with rolling context manager e772ddf

Pin vllm-i64 dynamic model metadata

Report maintenance while checkpoint upload completes

Deploy TR-MOE-306 with vllm-i64

initial commit