This website requires JavaScript.
Explore
Help
Sign In
Gahow Wang
gahow
0 Followers
·
0 Following
Joined on
2026-04-03
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
User to block:
Optional note:
The note is not visible to the blocked user.
Cancel
Block
Repositories
19
Projects
Packages
Public Activity
Starred Repositories
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-25 02:50:54 +00:00
6a27f75337
Docs: reconcile routing docs with current hybrid direction
ac6534c3ff
Cleanup: retire dead PUSH path + extract hybrid picker
255c8e6884
Hybrid routing: LMetric for LB + explicit affinity for high-cache sessions
448361cf83
Update design doc: final results + review findings
4c583f2f1c
Revert relaxed gate + push_cost fix: 134 offloads destroyed performance
Compare 10 commits »
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-24 14:45:15 +00:00
5772149d36
Approach B v2: TTFT-based migration trigger
45b82272c3
Add migration policy design doc with A/B experiment results
e9919605af
Approach B: session-level lazy migration trigger
e06de5144b
Approach A: contention-aware cost model with migration discount
e13391eeab
Evict migrated blocks from prefix cache after KV send completes
Compare 61 commits »
gahow
pushed to
main
at
gahow/xserv
2026-05-23 06:14:00 +00:00
9bb5c5c328
tools: add correctness + performance test scripts for Qwen3-8B
986a289616
fix: 12 bug fixes from comprehensive review — 51 tok/s verified on RTX 5090
Compare 2 commits »
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 23:16:32 +00:00
8e0c6e78b0
Add comprehensive research findings document
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 23:15:03 +00:00
080a8fa138
Chunk-size ablation + comprehensive synthesis
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 21:51:48 +00:00
baf7ffb08c
16-session contention: TPOT +45% from prefill-decode interference
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 19:04:04 +00:00
85b230455e
H7 OVERLOAD_FACTOR sweep: negative result + H4 GPU profiling
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 18:14:40 +00:00
3bc37cc6d5
PS experiments + H4 cache-gate + GPU profiling + Mooncake elif→if fix
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 17:17:13 +00:00
098d86385a
Add elastic hypotheses tracking doc with H1-H6 analysis
gahow
pushed to
main
at
gahow/quant-trading
2026-05-22 16:45:54 +00:00
0d983edfc0
research: individual stock swing, new frameworks, literature alpha, DCA
gahow
pushed to
main
at
gahow/xserv
2026-05-22 16:39:28 +00:00
a67e724119
docs: Phase 15 design doc + benchmark report
gahow
pushed to
main
at
gahow/xserv
2026-05-22 15:57:36 +00:00
d5532ef209
phase 15: Tensor::empty + CUDA Graph infra — 50.3 tok/s (140% of HF, 45% roofline)
gahow
pushed to
main
at
gahow/xserv
2026-05-22 14:22:33 +00:00
e207523e21
phase 15: custom GEMV kernel — 46.6 tok/s serial (3.5x improvement, 130% of HF)
gahow
pushed to
main
at
gahow/xserv
2026-05-22 12:07:45 +00:00
876d3f5d6a
phase 15: batched decode forward — 35 tok/s (97% of HF transformers)
gahow
pushed to
main
at
gahow/xserv
2026-05-22 11:41:04 +00:00
9783fcf410
phase 15: decode attention kernel + fused silu_mul + fused add_rmsnorm
gahow
pushed to
main
at
gahow/xserv
2026-05-22 10:51:40 +00:00
6cc1c9332d
docs: Phase 14 design doc + benchmark, fix Phase 11/12 honesty
d67dda404e
phase 14: Flash Attention 2 for SM120 (RTX 5090)
ee68d3565d
fix: comprehensive review + 14 bug fixes + Phase 12/14 overhaul
Compare 3 commits »
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 09:54:29 +00:00
fc92410ec9
Invalidate prior A/B results + add proper experiment harness
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 08:57:43 +00:00
e4fa56cb1e
LMetric routing policy (OSDI'26) + A/B results vs linear baseline
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 08:17:51 +00:00
2b0ac70ee7
Phase 1 milestone: system-level analysis + reproducible report
gahow
pushed to
main
at
gahow/agentic-kvc
2026-05-22 07:48:53 +00:00
1e8628581b
Fair A/B: Elastic P2P wins on ALL metrics vs baseline (fresh restart)
First
Previous
...
30
31
32
33
34
...
Next
Last