frida-andersson 71fc70d3ae [ROCm][DSv4] Fix sparse-indexer logits collapse on gfx950/gfx942 (#50455) ...

Signed-off-by: Frida Andersson <fanderss@amd.com>
Signed-off-by: frida-andersson <fanderss@amd.com>

2026-09-18 16:57:44 +00:00

..

attention

[ROCm][DSv4] Fix sparse-indexer logits collapse on gfx950/gfx942 (#50455)

2026-09-18 16:57:44 +00:00

core

[Bugfix][HiSparse][NIXL] Import full blocks without tail prefill on D (#57049)

2026-09-17 15:26:10 -04:00

engine

[Core] Make parallel sampling (n>1) reqs admission atomic (#53936)

2026-09-18 18:08:44 +02:00

executor

[Frontend][Core] Add release_kv_cache_memory() API (#44890)

2026-09-18 07:12:12 +08:00

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

hisparse

[Bugfix][HiSparse][NIXL] Import full blocks without tail prefill on D (#57049)

2026-09-17 15:26:10 -04:00

kv_offload

[Bugfix][ROCm][KV Offload] Use private pinned tensors for CPU KV offload (#57160)

2026-09-18 02:35:23 +00:00

metrics

[Bugfix][Metrics] Do not log a 0.0% prefix cache hit rate before any query (#54990)

2026-09-17 18:19:13 +00:00

pool

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)

2026-08-24 08:33:32 -04:00

sample

[Bugfix] Fall back to native sampling when FlashInfer cannot target the GPU (#48956)

2026-09-17 12:27:54 +00:00

simple_kv_offload

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

spec_decode

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

structured_output

[Bugfix] Escape control characters in xgrammar choice grammar (#48115)

2026-09-17 15:57:47 +03:00

watermarking

[watermarking] Dual-key gumbel-max watermarking for speculative decoding support (#56122)

2026-09-12 18:42:01 +00:00

worker

[Bugfix][DBO] Fix DeepEP low-latency profiling crash with DP+EP+DBO (#57502)

2026-09-18 06:33:41 +00:00

__init__.py

…

cudagraph_dispatcher.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

kv_cache_interface.py

[Bugfix][KV Cache][GLM-5.3-Flash] Disable slot mapping kernel for the kpool tail buffer (#57317)

2026-09-17 22:42:54 -04:00

kv_cache_layout.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

kv_cache_spec_registry.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

outputs.py

[EC Connector] Add Metrics Collection (#54960)

2026-09-17 10:36:23 +08:00

request.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

serial_utils.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

utils.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00